Search

Remote sensing Hyperspectral Image (HSI) has attracted researchers as a rich source of information. A recent trend in HSI analysis directs research to combine features of spatial nature with spectral nature. The motivation was that contiguous pixels share spectral features due to the low spatial resolution. This paper introduces an incremental work to a proposed approach that clusters HSI using K-means and combines spatial and spectral features together. The proposed approach uses selects pixels neighborhood, named kernel, from HSI to represent a cluster. For each cluster, pixels' bands box-plots profile is built to represent cluster bands distribution. Hence, the profile interprets the spectral features of a cluster. The approach starts by selecting K kernels from the given image scene randomly. However, results are affected by this random selection. In this paper, kernels are selected randomly but, they will be subjected to a test that avoids negative effect of randomness and prevents clusters to be represented again. In other words, the test ensures that successive kernels are different than previous selected kernels. Successive kernels are mapped against previous kernels box-plots profiles. Only kernels that prove to be spectrally different are used to represent consecutive clusters centroids. A pixel will join the cluster which score the minimum number of outlier reflectance values. [ABSTRACT FROM AUTHOR]

Remote sensing Hyperspectral Image (HSI) has attracted researchers as a rich source of information. A recent trend in HSI analysis directs research to combine features of spatial nature with spectral nature. The motivation was that contiguous pixels share spectral features due to the low spatial resolution. This paper introduces an incremental work to a proposed approach that clusters HSI using K-means and combines spatial and spectral features together. The proposed approach uses selects pixels neighborhood, named kernel, from HSI to represent a cluster. For each cluster, pixels' bands box-plots profile is built to represent cluster bands distribution. Hence, the profile interprets the spectral features of a cluster. The approach starts by selecting K kernels from the given image scene randomly. However, results are affected by this random selection. In this paper, kernels are selected randomly but, they will be subjected to a test that avoids negative effect of randomness and prevents clusters to be represented again. In other words, the test ensures that successive kernels are different than previous selected kernels. Successive kernels are mapped against previous kernels box-plots profiles. Only kernels that prove to be spectrally different are used to represent consecutive clusters centroids. A pixel will join the cluster which score the minimum number of outlier reflectance values. [ABSTRACT FROM AUTHOR]

Remote sensing Hyperspectral Image (HSI) has attracted researchers as a rich source of information. A recent trend in HSI analysis directs research to combine features of spatial nature with spectral nature. The motivation was that contiguous pixels share spectral features due to the low spatial resolution. This paper introduces an incremental work to a proposed approach that clusters HSI using K-means and combines spatial and spectral features together. The proposed approach uses selects pixels neighborhood, named kernel, from HSI to represent a cluster. For each cluster, pixels' bands box-plots profile is built to represent cluster bands distribution. Hence, the profile interprets the spectral features of a cluster. The approach starts by selecting K kernels from the given image scene randomly. However, results are affected by this random selection. In this paper, kernels are selected randomly but, they will be subjected to a test that avoids negative effect of randomness and prevents clusters to be represented again. In other words, the test ensures that successive kernels are different than previous selected kernels. Successive kernels are mapped against previous kernels box-plots profiles. Only kernels that prove to be spectrally different are used to represent consecutive clusters centroids. A pixel will join the cluster which score the minimum number of outlier reflectance values. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new feature selection method for hyperspectral images. Firstly, the bands are selected by combining the information entropy, classification separability and correlation coefficients with the Choquet fuzzy integral. After that, maximum likelihood classification method is used for the classification. Experiments on the AVIRIS dataset show that the proposed method removes the redundant spectral bands effectively. [ABSTRACT FROM AUTHOR]

The attention given recently for Hyperspectral Images (HSI) in remote sensing was due to its spectral nature used in earth surface exploration. Recently, researches proposed approaches that combine features of spatial nature with spectral nature to enhance HSI analysis accuracy. The reason behind this orientation is that contiguous pixels mostly share spectral features due to the low spatial resolution. In this paper, authors follow this orientation in clustering HSI using K-means. The proposed approach uses kernels, group of spatially neighbored pixels, to build profile for each cluster. The profile preserves cluster's spectral nature through its bands' Box-Plots that were extracted from selected kernels. The approach starts by selecting K kernels from the given image scene randomly instead of generating random kernels. Then a profile for each cluster is built using the selected kernel pixels' spectrums. The profile consists of b box-plots, where b is the number of bands. Each band box-plot interprets the spread of contiguous pixels' reflectance values in that band. Each pixel in the image will join the nearest cluster. The distance to be measured between any given pixel spectrum and cluster's centroid is replaced by counting how many reflectance values have been considered outlier to their corresponding band's box-plot in that cluster profile. The pixel will join the cluster with minimum outlier count. The profiles are updated iteratively using the new pixels distribution. Data sets used in the experiments are captured by Hyperion Earth Observer 1 (EO-1) sensor. [ABSTRACT FROM AUTHOR]

The attention given recently for Hyperspectral Images (HSI) in remote sensing was due to its spectral nature used in earth surface exploration. Recently, researches proposed approaches that combine features of spatial nature with spectral nature to enhance HSI analysis accuracy. The reason behind this orientation is that contiguous pixels mostly share spectral features due to the low spatial resolution. In this paper, authors follow this orientation in clustering HSI using K-means. The proposed approach uses kernels, group of spatially neighbored pixels, to build profile for each cluster. The profile preserves cluster's spectral nature through its bands' Box-Plots that were extracted from selected kernels. The approach starts by selecting K kernels from the given image scene randomly instead of generating random kernels. Then a profile for each cluster is built using the selected kernel pixels' spectrums. The profile consists of b box-plots, where b is the number of bands. Each band box-plot interprets the spread of contiguous pixels' reflectance values in that band. Each pixel in the image will join the nearest cluster. The distance to be measured between any given pixel spectrum and cluster's centroid is replaced by counting how many reflectance values have been considered outlier to their corresponding band's box-plot in that cluster profile. The pixel will join the cluster with minimum outlier count. The profiles are updated iteratively using the new pixels distribution. Data sets used in the experiments are captured by Hyperion Earth Observer 1 (EO-1) sensor. [ABSTRACT FROM AUTHOR]

Spectral Mixture Analysis (SMA) has been widely utilized to address the mixed-pixel problem in the quantitative analysis of hyperspectral remote sensing images. Recently Nonnegative Matrix Factorization (NMF) has been successfully utilized to simultaneously perform endmember extraction (EE) and abundance estimation (AE). In this paper, we formulate the solution of NMF by performing EE and AE iteratively. Based on our previous Hopfield Neural Network (HNN) based AE algorithm, an HNN is also constructed for EE to solve the multiplicative updating problem of NMF for SMA. As a result, SMA is conducted in an unsupervised manner and our algorithm is able to extract virtual endmembers without assuming the presence of spectrally pure constituents in hyperspectral scenes. We further extend such strategy to solve the constrained NMF (cNMF) models for SMA, where extra constraints are imposed to better model the mixed-pixel problem. Experimental results on both synthetic and real hyperspectral images demonstrate the effectiveness of our proposed HNN based unsupervised SMA algorithms. [ABSTRACT FROM PUBLISHER]

Hyperspectral images exhibit significant spectral correlation, whose exploitation is crucial for compression. In this paper, an efficient method for hyperspectral image compression is presented using the three-dimensional discrete cosine transform (3D-DCT) and support vector machine (SVM). The core idea behind our proposed technique is to apply SVM on the 3D-DCT coefficients of hyperspectral images in order to determine which coefficients (support vectors) are more critical for being preserved. Our method not only exploits redundancies between the bands, but also uses spatial correlations of every image band. Consequently, as simulation results applied to real hyperspectral images demonstrate, the proposed method leads to a remarkable compression ratio and quality. [ABSTRACT FROM PUBLISHER]

The N-FINDER algorithm is widely used for endmember extraction from hyperspectral images. One of the disadvantages of N-FINDER is that its sequential implementations have long run times due to their relatively large computational complexity. A fast parallel version of N-FINDER is developed in this paper. This version combined with the use of Hyperspectral Image Reduction for Endmember Extraction technique (HIREE) provides an algorithm that is 8 times faster than the original N-FINDER sequential algorithm. [ABSTRACT FROM PUBLISHER]

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

Hyperspectral images (HSI) classification is a high technical remote sensing tool. The main goal is to classify the point of a region. The HIS contains more than a hundred bidirectional measures, called bands (or simply images), of the same region called Ground Truth Map (GT). Unfortunately, some bands contain redundant information, others are affected by the noise, and the high dimensionalities of features make the accuracy of classification lower. All these bands can be important for some applications, but for the classification a small subset of these is relevant. In this paper we use mutual information (MI) to select the relevant bands; and the Normalized Mutual Information coefficient to avoid and control redundant ones. This is a feature selection scheme and a Filter strategy. We establish this study on HSI AVIRIS 92AV3C. This is effectiveness, and fast scheme to control redundancy. [ABSTRACT FROM PUBLISHER]

In this paper we propose a novel and efficient model for compressed sensing of hyperspectral images. A large-size hyperspectral image can be subsampled by retaining only 3% of its original size, yet robustly recovered using the new approach we present here. Our reconstruction approach is based on minimizing a convex functional which penalizes both the trace norm and the TV norm of the data matrix. Thus, the solution tends to have a simultaneous low-rank and piecewise smooth structure: the two important priors explaining the underlying correlation structure of such data. Through simulations we will show our approach significantly enhances the conventional compression rate-distortion tradeoffs. In particular, in the strong undersampling regimes our method outperforms the standard TV denoising image recovery scheme by more than 17dB in the reconstruction MSE. [ABSTRACT FROM PUBLISHER]

Hyperspectral image is a substitution of more than a hundred images, called bands, of the same region. They are taken at juxtaposed frequencies. The reference image of the region is called Ground Truth map (GT). the problematic is how to find the good bands to classify the pixels of regions; because the bands can be not only redundant, but a source of confusion, and decreasing so the accuracy of classification. Some methods use Mutual Information (MI) and threshold, to select relevant bands. Recently theres an algorithm selection based on mutual information, using bandwidth rejection and a threshold to control and eliminate redundancy. The band top ranking the MI is selected, and if its neighbors have sensibly the same MI with the GT, they will be considered redundant and so discarded. This is the most inconvenient of this method, because this avoids the advantage of hyperspectral images∷ some precious information can be discarded. In this paper well make difference between useful and useless redundancy. A band contains useful redundancy if it contributes to decreasing error probability. According to this scheme, we introduce new algorithm using also mutual information, but it retains only the bands minimizing the error probability of classification. To control redundancy, we introduce a complementary threshold. So the good band candidate must contribute to decrease the last error probability augmented by the threshold. This process is a wrapper strategy; it gets high performance of classification accuracy but it is expensive than filter strategy. [ABSTRACT FROM PUBLISHER]

Nonnegative Matrix Factorization (NMF) has been successfully employed to address the mixed-pixel problem of hyperspectral remote sensing images. However, minimizing the representation error by NMF is not sufficient for SMA since the unmixing results of NMF are not unique. Therefore, in this paper, a neighborhood preserving regularization, which preserves the local structure of the hyperspectral data on a low-dimensional manifold, is proposed to constrain NMF for unique solution in SMA. As a result, a Neighborhood Preserving constrained NMF (NP-NMF) algorithm is proposed for SMA of highly mixed hyperspectral data. Finally, experimental results on AVIRIS data demonstrate the effectiveness of our proposed NP-NMF algorithm for SMA applications. [ABSTRACT FROM PUBLISHER]

This paper presents a new multiple-classifier approach for accurate spectral-spatial classification of hyperspectral images, where the spectral information is exploited by combining probabilistic support vector machines (SVM) and subspace-based multinomial logistic regression (MLRsub) and the spatial information is exploited by means of a Markov random field (MRF) regularizer. The proposed approach is based on the decision fusion of global posterior probability distributions and local probabilities which result from the whole image and the class combinations map respectively. With respect to the SVM or MLRsub algorithms, the proposed method greatly improves the classification accuracy. Our experimental results with real hyperspectral images collected by the NASA Jet Propulsion Laboratory's Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) and the Reflective Optics Spectrographic Imaging System (ROSIS), indicate that the proposed multiple-classifier system leads to state-of-the-art classification performance for cases with very limited number of training samples. [ABSTRACT FROM PUBLISHER]

With the introduction of manifold assumption, Laplacian Support Vector Machine (LapSVM) has advantages over the traditional SVM classifiers. However the dual solution of LapSVM is still a major barrier on the further application of LapSVM. Primal optimization is a promising solution to this problem. In this paper, we introduce a novel primal Laplacian Support Vector Machine with Precondition Conjugate Gradient method (PCG) to the problem of hyperspectral images classification which is one type of primal optimization solution. To prove the effectiveness of the proposed method, we apply it into the hyperspectral image data set Indian Pine. The experiment results show higher accuracy and better generalization ability than dual strategy. [ABSTRACT FROM PUBLISHER]

The well-known difficulty in supervised hyperspectral image classification is the limited availability of training data, which are expensive, and quite difficult to access and to obtain in real remote sensing scenarios. The Support Vector Machine (SVM) technique has been proven to be well suited to classify hyperspectral data by using limited number of training samples. In this paper, modifications over Iterative Support Vector Machine algorithm have been proposed incorporating both spatial and spectral information and correcting the training samples at each iteration in order to increase the classification performance over SVM. In order to demonstrate the effectiveness of the proposed framework, experiments on AVIRIS data over Indian Pine Site (IPS) are conducted to compare the performance of the proposed classification approach against some existing classification techniques such as Linear-SVM, SVM-RBF, ISVM and K-NN. Experimental results demonstrate that the proposed method clearly outperform the well-known classification algorithms. [ABSTRACT FROM PUBLISHER]

This paper addressed the change-detection problem in multitemporal hyperspectral remote sensing images (CD-HS). The concept of “change” in multitemporal hyperspectral images is analyzed from the viewpoint of single pixel spectral signal. A novel hierarchical change-detection approach is proposed by considering both the change magnitude and spectral change information, which aims to identify the change classes having discriminable spectral behaviors. The proposed method is developed in an unsupervised way thus to provide a solution for real CD-HS cases, for which reference samples are often not available. Experimental results obtained on multitemporal Hyperion hyperspectral images confirm the effectiveness of the proposed change-detection approach. [ABSTRACT FROM PUBLISHER]

One of the most important problems in classification of Hyperspectral images is Hughes phenomena. The main reason for this problem is high dimension feature space and deficiency of training samples. To solve this kind of problem, so many methods are applied which some of them emphasize feature reduction and the others point to classification method with low sensitivity to training samples or consider spatial information or semi supervised training samples. In feature reduction algorithms intensity vectors of pixels are used individually. Additionally, in most of such techniques each component of intensity vector is considered as an individual element without attention to inner relation among them. In this paper we consider members of intensity vector as sampling points of spectral reflecting curve (SRC) of corresponding land cover (LC) and use fractal features of SRC in order to classify the picture. Moreover, we will show using these features improve the classification results in multispectral images. [ABSTRACT FROM PUBLISHER]

One of problems that have been not considered in unmixing process of hyperspectral is the correlation between bands. This correlation makes difficult the unmixing of spectral signatures of different materials. Furthermore, the large number of spectral bands extends the execution time of the unmixing process. In this paper, a new approach for the unmixing of hyperspectral data using the semi-Nonnegative Matrix Factor (semi-NMF) and Principal Component Analysis (PCA) is proposed that solves the problem of correlation between bands and decrease execution time of algorithm. The proposed approach uses from PCA of data in the unmixing process instead of original data. Using this linear transformation, the images are mapped to the uncorrelated space. Uncorrelated images make more efficient the unmixing process. In order to overcome the problem of non-uniqueness solution that is caused by the non-convex cost function, the smoothness and sparseness constraints are introduced to the semi-NMF. In addition to its high accuracy, the proposed method increases the speed of the unmixing process. The experimental results show excellence of the proposed approach in comparison of other methods. [ABSTRACT FROM PUBLISHER]

in this paper, we propose a new linear feature extraction scheme for hyperspectral images. A modified Maximum relevance, Min redundancy (MRMD) is used as a criterion for linear feature extraction. Parzen density estimator and instantaneous entropy estimation are used for estimating mutual information. Using Instantaneous entropy estimator mitigates nonstationary behavior of the hyperspectral data and reduces computational cost. Based on proposed estimator and MRMD, an algorithm for linear feature extraction in hyperspectral images is designed that is less offended by Hueghs phenomenon and has less computation cost for applying to hyperspectral images. An ascent gradient algorithm is used for optimizing proposed criterion with respect to parameters of a linear transform. Preliminary results achieve better classification comparing the traditional methods. [ABSTRACT FROM PUBLISHER]

This paper presents a new methodology for automatically labeling extracted endmembers from hyperspectral images, using a reference Spectral Library (SL). The SL is structured with three main layers: main consisting material, semantic meaning, and illumination conditions in order to classify the endmembers. The labeling process is based on two similarity metrics: the Spectral Angle Mapper and the Cross Correlation. These two metrics are initially introduced in spectral inequalities which characterize each endmember of the reference SL. During the labeling procedure, inequalities should be respected for labeling the endmembers, otherwise the values of metrics are used. Updating of the SL refers to incorporation of the not labeled endmembers in the SL. Photo-interpretation methodology and SAM calculation for checking the shifted values due to illumination variations are required. The proposed methodology is evaluated using CASI-550 radiance images. The methodology produced satisfactory results. [ABSTRACT FROM PUBLISHER]

To improve the classification accuracy of image in which many classes have the similar spectrum, this paper presents a new hierarchical classification scheme for hyperspectral images (HSI). The Spectral Angle Mapping (SAM) is firstly used to combine the similar classes into large classes. Next the hierarchical classifier classifies the image with large classes and then divides every large class into normal classes further. For every large class, the most suitable feature extraction method and classifier are chosen empirically. Meanwhile, a new band selection is proposed to help every large class find the bands which can better reflect the differences of classes according to the characteristic of spectrum. Experiments are conducted on a 103-band ROSIS image of University of Pavia. The experimental results show that the hierarchical classifier is better than the single classifier used only once. Especially when the spectra of the given classes are so similar that the traditional classifiers couldn't divide them thoroughly, the proposed classifier can make it. Moreover, the hierarchical classifier can do more efficiently because it excludes some redundant bands and concentrates on the bands with slight differences. [ABSTRACT FROM PUBLISHER]

This paper presents a classification method for hyperspectral images utilizing Differential Morphological Profiles (DMPs) which permit to include in the analysis spatial information since they can provide an estimate of the size and contrast characteristics of the structures in an image. Due to the wide variety of objects present in a scene, the pixels belonging to the same semantic structure may not have homogeneous spatial and spectral features. In addition, instead of a single peak (which can be related to a measure of the scale), multiple local maxima and multiple responses are usually observed in the DMP. In order to handle such intra-class variability, class-specific weighting functions are employed in order to differently modulate the DMP values according to the different characteristics of the land cover types. In such way, it is possible to differentiate the behaviors of the DMP for each pixel in the image according to its semantic, providing an increase of the separability of the classes. At first, a DMP computed with opening by reconstruction (DMPO) and one with closing by reconstruction (DMPC) are derived on each of the first principle components extracted from the hyperspectral image. Then, both profiles are weighted by each class-specific weighting function and concatenated in a single data structure. The constructed feature vectors are considered by a random forest classifier. [ABSTRACT FROM PUBLISHER]

In this paper, we propose to improve the classification accuracy of hyperspectral images by fusing the capabilities of the support vector machine (SVM) classifier and the fuzzy C-means (FCM) clustering algorithm. While the former is used to generate a spectral-based classification map, the latter is adopted to provide an ensemble of clustering maps. To reduce the computation complexity, the most representative spectral channels identified by the Markov Fisher Selector (MFS) algorithm are used during the clustering process. Then, these maps are successively labeled via a pairwise relabeling procedure with respect to the SVM-based classification map using voting rules. To generate the final classification result, we propose to aggregate the obtained set of spectro-spatial maps through two different fusion methods based on voting rules and Markov Random Field (MRF) theory. [ABSTRACT FROM PUBLISHER]

Hyperspectral-based change detection is often inadvertently affected by image artifacts, reducing the accuracy of the change detector. We present a Hyperspectral Change Detection (HSCD) process to distinguish parallax-induced change from legitimate change. Image parallax decreases the accuracy of change detection results. The approach introduced in this paper utilizes a combination of a spectral change detector and stereo geometry to reduce parallax-induced false alarms. Image parallax is determined by considering the error in the epipolar constraint, meaning the corresponding points between two images must lie on epipolar lines. Experimental analysis shows a false alarm reduction by nearly one order of magnitude on synthetic hyperspectral imagery and nearly two orders of magnitude on real hyperspectral imagery. [ABSTRACT FROM PUBLISHER]

Hyperspectral images (HSI) contain hundreds of bands, which brings huge amount of data. In this paper, a novel compression method based on optimal-truncation tucker decomposition for HSI is proposed. HSI tensor is firstly decomposed into complete core tensor. And then core tensor and factor matrices are truncated according to the optimal number of components of core tensor along each mode (NCCTEM), which is determined by the proposed criterion for the optimal NCCTEM and searching strategy. Experimental results show that the proposed method has the excellent reconstruction comparable to the traditional compression methods. Furthermore, it significantly reduces the compression and decompression time. [ABSTRACT FROM PUBLISHER]

This paper describes a Gaussian process based method for nonlinear hyperspectral image unmixing. The proposed model assumes a nonlinear mapping from the abundance vectors to the pixel reflectances contaminated by an additive white Gaussian noise. The parameters involved in this model satisfy physical constraints that are naturally expressed within a Bayesian framework. The proposed abundance estimation procedure is applied simultaneously to all pixels of the image by maximizing an appropriate posterior distribution which does not depend on the endmembers. After determining the abundances of all image pixels, the endmembers contained in the image are estimated by using Gaussian process regression. The performance of the resulting unsupervised unmixing strategy is evaluated through simulations conducted on synthetic data. [ABSTRACT FROM PUBLISHER]

Hyperspectral endmember extraction (EE) is to estimate endmember signatures (or material spectra) from the hyperspectral data of an unexplored area for analyzing the materials and their composition therein. However, the presence of noise in the data posts a serious problem for EE. Recently, robustness against noise has been taken into account in the design of EE algorithms. The robust maximum-volume simplex criterion [1] has been shown to yield performance improvement in the noisy scenario, but its real applicability is limited by its high implementation complexity. In this paper, we propose two fast algorithms to approximate this robust criterion [1], which turns out to deal with a set of partial max-min optimization problems in alternating manner and successive manner, respectively. Some Monte Carlo simulations demonstrate the superior computational efficiency and efficacy of the proposed robust algorithms in the noisy scenario over the robust algorithm in [1] and some benchmark EE algorithms. [ABSTRACT FROM PUBLISHER]

N-FINDER algorithm is widely used for endmember extraction. One of the disadvantages of N-FINDER is that its implementations take long run time due to the relatively large computational complexity of N-FINDER. Successfully reducing the size of the input data set -the hyperspectral image - that the algorithm works on can reduce the overall run time of the algorithm. A method for successfully selecting the proper sample of the data set to work on is provided in this paper. Using this reduction technique, a faster and statistically more accurate version of N-FINDER is presented. [ABSTRACT FROM PUBLISHER]

Nowadays the detection in space environment is definitely a hot spot in the whole world. Developing the technique of multiple materials detection makes great sense. In this paper, we propose an algorithm for spatial multiple materials detection in hyperspectral images. The detection problem is a semi-blind signal extraction problem. As the prior knowledge, the spectra of target materials are known in advance. The proposed detection algorithm, multiple materials detector (MMD), exploits spectral information exclusively to make decisions by considering that the type of each pixel contains the interesting materials or not, which is a semi-blind signal extraction method. With this method, after single time detection of a hyperspectral image, the multiple materials spectra input before could be exactly detected. Compared with classical detection methods, the proposed detection method has three superiorities. Firstly, it functions well when there are various kinds of interesting materials needing to be detected. Secondly, because of using regularization items the algorithm is robust in spectral variability and noise. Lastly, no matter how the interesting materials distribute in the hyperspectral image, it works steadily. Experimental results based on a set of hyperspectral images of Hubble Space Telescope prove the effectiveness of the MMD algorithm. [ABSTRACT FROM PUBLISHER]

We propose a segmented PCA based distributed framework exploiting the high correlation and dimensionality reduction properties of PCA in conjugation with the distributed source coding paradigm for onboard hyperspectral image compression. The hybrid scheme deploying Lossy Wyner Ziv coding in conjunction with statistically segmented PCA strategy exploits the two fold intra group and inter group correlation for establishment of multiple independent processing elements evenly distributing the cumulative encoder load over the entire system. The net performance of this flexible infrastructure scheme is further increased by utilizing the superior rate distortion performance of JPEG2000 for high fidelity reconstruction of side information crucial for corresponding Wyner Ziv decoding. The inherent parallelism and low encoder complexity of the proposed scheme not only makes it a viable candidate for onboard implementation but also conforms it to subsequent multi-node transmission. Experimental analysis demonstrates that the proposed scheme offers a novel perspective and competitive performance as compared to other techniques in the same domain. [ABSTRACT FROM PUBLISHER]

Feature generation (i.e. feature selection/extraction) for hyperspectral images in pattern classification is one of the key elements in improving the accuracy of classifier. Nonetheless, most existing techniques encounter difficulties in extracting essential features of non-stationary and/or non-linear signal, let alone hyperspectral images. Here, an alternative technique motivated by bi-dimensional empirical mode decomposition (BEMD) is presented. By virtue of BEMD, the given signal is adaptively decomposed into a series of bi-dimensional intrinsic mode functions (BIMFs) with different oscillations. Furthermore, those BIMFs are integrated into new features of the original signal. Additionally, the recently developed fuzzy support vector machine (FSVM) is exhibited to classify those features so as to reduce effects of outliers or noises. Experimental results on the widely used 92AV3C hyperspectral dataset demonstrate the efficiency of the proposed approach. [ABSTRACT FROM PUBLISHER]