Search

A compressed sensing (CS) reconstruction algorithm of hyperspectral images jointly using spatial and spectral characteristics is considered. Specifically, in the sampling process, each band image is sampled by the block CS method independently. In the reconstruction process, how to utilize the spatial smoothing feature of each band image and spectral correlation between different band images to formulate the joint optimization problem is the focus of this paper. The total variation (TV) norm and multihypothesis prediction are introduced to express the spatial smoothing feature and the spectral correlation, respectively. Thus, the TV norm and the prediction residual are used as the regularization items in the reconstruction optimization problem. The resulting ill-posed problem is solved by the augmented Lagrange multiplier method and alternating direction method in an iterative way, and the implementation process of the reconstruction algorithm is presented. Experimental results on four hyperspectral datasets reveal that the proposed algorithm significantly outperforms alternative strategies in terms of peak signal-to-noise ratio as well as visual quality. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

Terrain classification is an important research direction in the field of remote sensing. Hyperspectral remote sensing image data contain a large amount of rich ground object information. However, such data have the characteristics of high spatial dimensions of features, strong data correlation, high data redundancy, and long operation time, which lead to difficulty in image data classification. A data dimensionality reduction algorithm can transform the data into low-dimensional data with strong features and then classify the dimensionally reduced data. However, most classification methods cannot effectively extract dimensionality-reduced data features. In this paper, different dimensionality reduction and machine learning supervised classification algorithms are explored to determine a suitable combination method of dimensionality reduction and classification for hyperspectral images. Soft and hard classification methods are adopted to achieve the classification of pixels according to diversity. The results show that the data after dimensionality reduction retain the data features with high overall feature correlation, and the data dimension is drastically reduced. The dimensionality reduction method of unified manifold approximation and projection and the classification method of support vector machine achieve the best terrain classification with 99.57% classification accuracy. High-precision fitting of neural networks for soft classification of hyperspectral images with a model fitting correlation coefficient (R2) of up to 0.979 solves the problem of mixed pixel decomposition. [ABSTRACT FROM AUTHOR]

An accurate identification of objects from the acquisition system depends on the clear segmentation and classification of remote sensing images. With the limited financial resources and the high intra-class variations, the earlier proposed algorithms failed to handle the sub-optimal dataset. The building of an efficient training set iteratively in active learning (AL) approaches improves classification performance. The heuristics-based AL provides better results with the inheritance of contextual information and the robustness to noise variations. The uncertainty exists pixel variations make the heuristics-based AL fail to handle the remote sensing image classification. Previously, we focused on the extraction of clear textural pattern information by using the extended differential pattern-based relevance vector machine (EDP-AL). This paper extends that work into the novel pixel-certainty activity learning (PCAL) based on the information about textural patterns obtained from the extended differential pattern (EDP). Initially, distributed intensity filtering (DIF) is used to eliminate noise from the image, and then histogram equalization (HE) is used to improve the image quality. The EDP is used to merge and classify different labels for each image sample, and this algorithm expresses the textural information. The PCAL technique is used to classify the HSI patterns that are important in remote sensing applications using this pattern collection. Pavia University and Indian Pines (IP) are the datasets used to validate the performance of the proposed PCAL (PU). The ability of PCAL to accurately categorize land cover types is demonstrated by a comparison of the proposed PCAL with existing algorithms in terms of classification accuracy and the Kappa coefficient. [ABSTRACT FROM AUTHOR]

Hyperspectral images constitute a substantial amount of data in the form of spectral bands. This information is used for land cover analysis, specifically in classifying a hyperspectral pixel, which is a popular domain in remote sensing. This paper proposed an efficient framework to classify spectral-spatial hyperspectral images by employing multiobjective optimization. Spectral-spatial features of hyperspectral images are passed for optimization. As hyperspectral images have a high dimensional feature set, many classifiers cannot perform well. Multiobjective optimization reduces the feature set without affecting the discrimination ability of the classifier. The proposed work is validated on a standard hyperspectral image set, Pavia University and Kennedy Space Centre. [ABSTRACT FROM AUTHOR]

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this regard, a regularization term is typically aggregated to the cost function to consider prior information about a particular property of the covariance matrix. Hence, this paper proposes an algorithm based on the projected gradient method to recover low-rank or Toeplitz approximations of the covariance matrix from compressive measurements. The proposed algorithm divides the compressive measurements into data subsets projected onto different subspaces and accurately estimates the covariance matrix by solving a single optimization problem assuming that each data subset contains an approximation of the signal statistics. Furthermore, gradient filtering is included at every iteration of the proposed algorithm to minimize the estimation error. The error induced by the proposed splitting approach is analytically derived along with the convergence guarantees of the proposed method. The proposed algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples. Extensive simulations show that the proposed algorithm can effectively recover the covariance matrix of hyperspectral images from compressive measurements with high compression ratios ($8-15\%$ approx) in noisy scenarios. Moreover, simulations and theoretical results show that the filtering step reduces the recovery error up to twice the number of eigenvectors. Finally, an optical implementation is proposed, and real measurements are used to validate the theoretical findings. [ABSTRACT FROM AUTHOR]

A crucial task in hyperspectral image (HSI) taxonomy is exploring effective methodologies to effusively practice the 3-D and spectral data delivered by the statistics cube. For classification of images, 3-D data is adjudged in the phases of pre-cataloging, an assortment of a sample, classifiers, post-cataloging, and accurateness estimation. Lastly, a viewpoint on imminent examination directions for proceeding 3-D and spectral approaches is untaken. In topical years, sparse representation is acknowledged as a dominant classification tool to effectually labels deviating difficulties and extensively exploited in several imagery dispensation errands. Encouraged by those efficacious solicitations, sparse representation (SR) has likewise been presented to categorize HSI's and validated virtuous enactment. This research paper offers an overview of the literature on the classification of HSI technology and its applications. This assessment is centered on a methodical review of SR and support vector machine (SVM) grounded HSI taxonomy works and equates numerous approaches for this matter. We form an outline that splits the equivalent mechanisms into spectral aspects of systems, and spectral--spatial feature networks to methodically analyze the contemporary accomplishments in HSI taxonomy. Furthermore, cogitating the datum that accessible training illustrations in the remote distinguishing arena are generally appropriate restricted besides training neural networks (NNs) to necessitate an enormous integer of illustrations, we comprise certain approaches to increase taxonomy enactment, which can deliver certain strategies for imminent learnings on this issue. Lastly, numerous illustrative neural learning-centered taxonomy approaches are piloted on physical HSI's in our experimentations. [ABSTRACT FROM AUTHOR]

Superpixel segmentation (SS) methods have been proven to be feasible in improving the performance of hybrid algorithms on hyperspectral images (HSIs). In this paper, a superpixel segmentation algorithm based on the information measures with color histogram driving (IM-CHD) was proposed. First, Shannon entropy was applied to measure the image information and preliminarily select spectral bands. Mutual information (MI) is derived from the concept of entropy and measures the statistical dependence between two random variables. Also, MI can effectively identify the redundant spectral bands. Therefore, in this paper, both MI and color matching functions (CMF) were used to select the most useful spectral bands. Second, the selected spectral bands were combined into a false color image containing the main spectral information. A local optimization algorithm named "hill climbing" was used to achieve the superpixel segmentation. Finally, parameter selection experiments and comparative experiments were performed on two hyperspectral data sets. The experimental results showed that the IM-CHD method was more efficient and accurate than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The problem of pixel mixture, which is caused by low spatial resolution and complex land cover, restricts the development of target classification and detection for hyperspectral images (HSIs) in many application fields. In this paper, a novel sub-pixel spectral clustering algorithm of quantum mechanism effect is proposed for hyperspectral remote sensing images. In order to effectively describe the energy distribution of spectral vectors, we define a nonlinear mixture mathematic model with self-consistency for mixed pixel. Considering the self-consistent conditions between lattice models and quantum impurity model, Green function method is used to design the clusters mean field impurities solver, which can decompose the mixed spectral accurately and quickly. Finally, the spectral samples with smaller quantum potential energy and greater local density are applied as cluster center to obtain the final clustering result. The effectiveness of this method is illustrated on several hyperspectral remote sensing images, and experiments show that it can improve the ability of clustering high dimensional non-spherical structure data. [ABSTRACT FROM AUTHOR]

The accurate and timely monitoring of land cover types is of great significance for the scientific planning, rational utilization, effective protection and management of land resources. In recent years, land cover classification based on hyperspectral images and the collaborative representation (CR) model has become a hot topic in the field of remote sensing. However, most of the existing CR models do not consider the problem of sample imbalance, which affects the classification performance of CR models. In addition, the Tikhonov regularization term can improve the classification performance of CR models, but greatly increases the computational complexity of CR models. To address the above problems, a local nearest neighbor (LNN) method is proposed in this paper to select the same number of nearest neighbor samples from each nearest class of the test sample to construct a dictionary. This is then introduced into the original collaborative representation classification (CRC) method and CRC with Tikhonov regularization (CRT) for land cover classification, denoted as LNNCRC and LNNCRT, respectively. To verify the effectiveness of the proposed LNNCRC and LNNCRT methods, the classification performance and running time of the proposed methods are compared with those of six popular CR models on a hyperspectral scene with nine land cover types. The experimental results show that the proposed LNNCRT method achieves the best land cover classification performance, and the proposed LNNCRC and LNNCRT methods not only further exclude the interference of irrelevant training samples and classes, but also effectively eliminate the influence of imbalanced training samples, so as to improve the classification performance of CR models and effectively reduce the computational complexity of CR models. [ABSTRACT FROM AUTHOR]

Informative feature extraction from hyperspectral image (HSI) is the primary and most challenging task in the hyperspectral data processing. The rich source of HSI information provides effective ground cover analysis which requires high computational cost and, using the original, classification accuracy suffers from the curse of dimensionality. Therefore, feature reduction has been applied through feature extraction and feature selection. The popularly used unsupervised feature extraction method, Minimum Noise Fraction (MNF), has been applied but the computational cost is high. This paper proposed a band grouping technique using Normalized Mutual Information (NMI) and applies MNF to each individual group called BgMNF. Feature selection can be done with NMI. The extracted feature can be classified using kernel Support Vector Machine (SVM) for performance analysis. Two real HSI is used in experimentation that demonstrates the proposed technique significantly improves the classification accuracy as well as computational cost as compared with the studied methods. [ABSTRACT FROM AUTHOR]

Due to sensor instability and atmospheric interference, hyperspectral images (HSIs) often suffer from different kinds of noise which degrade the performance of downstream tasks. Therefore, HSI denoising has become an essential part of HSI preprocessing. Traditional methods tend to tackle one specific type of noise and remove it iteratively, resulting in drawbacks including inefficiency when dealing with mixed noise. Most recently, deep neural network-based models, especially generative adversarial networks, have demonstrated promising performance in generic image denoising. However, in contrast to generic RGB images, HSIs often possess abundant spectral information; thus, it is non-trivial to design a denoising network to effectively explore both spatial and spectral characteristics simultaneously. To address the above issues, in this paper, we propose an end-to-end HSI denoising model via adversarial learning. More specifically, to capture the subtle noise distribution from both spatial and spectral dimensions, we designed a Residual Spatial-Spectral Module (RSSM) and embed it in an UNet-like structure as the generator to obtain clean images. To distinguish the real image from the generated one, we designed a discriminator based on the Multiscale Feature Fusion Module (MFFM) to further improve the quality of the denoising results. The generator was trained with joint loss functions, including reconstruction loss, structural loss and adversarial loss. Moreover, considering the lack of publicly available training data for the HSI denoising task, we collected an additional benchmark dataset denoted as the Shandong Feicheng Denoising (SFD) dataset. We evaluated five types of mixed noise across several datasets in comparative experiments, and comprehensive experimental results on both simulated and real data demonstrate that the proposed model achieves competitive results against state-of-the-art methods. For ablation studies, we investigated the structure of the generator as well as the training process with joint losses and different amounts of training data, further validating the rationality and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper addresses an approach for the classification of hyperspectral imagery (HSI). In remote sensing, the HSI sensor acquires hundreds of images with narrow and continuous spectral width in visible and near-infrared regions of the electromagnetic (EM) spectrum. Such nature of data acquisition is very useful in the classification and/or the identification of different objects present in the HSI data. However, the low-spatial resolution and large volume of HS images make it more challenging. In the proposed approach, we use an autoencoder with convolutional neural network (AECNN) for the classification of HS images. Pre-processing with autoencoder enhances the features in the HS images which helps to obtain optimized weights in the initial layers of the CNN model. Hence, shallow CNN architecture can be utilized to extract features from the pre-processed HSI data which are used further for the classification of the same. The potential of the proposed approach has been verified by conducting many experiments on various datasets. The classification results obtained using the proposed method are compared with many state-of-the-art deep learning based methods including the winner of the geoscience and remote sensing society (GRSS) Image Fusion Contest-2018 on HSI classification held at IEEE International Geoscience and Remote Sensing Symposium (IGARSS)-2018 and it shows superiority over those methods. [ABSTRACT FROM AUTHOR]

Copyright of Entre Ciencia e Ingeniería is the property of Entre Ciencia e Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Spectral unmixing (SU) is a technique to characterize mixed pixels in hyperspectral images measured by remote sensors. Most of the spectral unmixing algorithms are developed using the linear mixing models. To estimate endmembers and fractional abundance matrices in a blind problem, nonnegative matrix factorization (NMF) and its developments are widely used in the SU problem. One of the constraints which was added to NMF is sparsity, that was regularized by $ L_ {q}$ norm. In this paper, a new algorithm based on distributed optimization is suggested for spectral unmixing. In the proposed algorithm, a network including single-node clusters is employed. Each pixel in the hyperspectral images is considered as a node in this network. The sparsity-constrained distributed unmixing is optimized with diffusion least mean p-power (LMP) strategy, and then the update equations for fractional abundance and signature matrices are obtained. Afterward, the proposed algorithm is analyzed for different values of LMP power and $ L_ {q}$ norms. Simulation results based on defined performance metrics illustrate the advantage of the proposed algorithm in spectral unmixing of hyperspectral data compared with other methods. [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]

Performance of deep convolutional neural network (CNN) has shown tremendous improvement when applied to various image classifications including hyperspectral images (HSIs). However, CNN requires a large number of labeled samples to train its parameters in different layers, the scarcity of which, in HSIs leads to overfitting problem. Prior integration of spectral-spatial information acts complementary to the deep features resulting in reduced computational load of deep CNN and also helps in mitigating overfitting problem. In this paper, we propose a CNN based classification model that first integrates spectral-spatial information by using an extended attribute profile constructed by selecting suitable threshold values automatically. Then, the constructed spectral-spatial features are utilized by 2D or 3D deep CNN models for classification. Experimental results on three real HSI data sets show that the proposed model can successfully integrate the individual strength of both the automatic extended attribute profile and deep CNN, and provide better classification accuracies. [ABSTRACT FROM AUTHOR]

In this work, an effective classification of hyperspectral images is modelled and simulated with the proximal support vector machine (PSVM) by integrating them with the deep learning approach. The modelled new deep proximal support vector machines are designed in a manner to handle the existing complexity, discrepancies and irregularities in the traditional hyperspectral image classifiers. This paper investigates the applicability of the new deep linear and nonlinear proximal support vector machines as applied for hyperspectral image classification. In respect of the new deep PSVM classifier, it is modelled for deep linear PSVM and deep nonlinear PSVM to perform classification of spectral images so as to bring out the best classifier model. To test and validate the proposed deep PSVM classifiers University of Pavia datasets, Indian Pine datasets and Kennedy Space Centre datasets are employed as test beds and results are attained. The developed new deep PSVM classifiers are developed with varied kernel functions to do the classification process. The deep learning technique enhances the linear and nonlinear PSVM classifier models to perform more effectively during the learning process and carry out the classification using auto-encoders and decoders. Results attained during the process infer that the developed new deep PSVM (linear and nonlinear) has come out with better classification accuracy in comparison with that of the other techniques from literature for the same datasets. Statistical analysis validates the randomness that occurs in the proposed deep learning techniques as applied for spectral image classification. [ABSTRACT FROM AUTHOR]

Multispectral (MS) and hyperspectral (HS) images have been successfully and widely used in remote sensing applications such as target detection, change detection, and anomaly detection. In this paper, we aim at reviewing recent change detection papers and raising some challenges and opportunities in the field from a practitioner's viewpoint using MS and HS images. For example, can we perform change detection using synthetic hyperspectral images? Can we use temporally-fused images to perform change detection? Some of these areas are ongoing and will require more research attention in the coming years. Moreover, in order to understand the context of our paper, some recent and representative algorithms in change detection using MS and HS images are included, and their advantages and disadvantages will be highlighted. [ABSTRACT FROM AUTHOR]

This paper introduces a new hyperspectral image denoising method called Non-local Convolutional Neural Network Denoiser (NL-CNND). The technique exploits data in four bands adjacent to the target one as additional information for the restoring process, and it uses a pre-denoising step based on BM4D. All the bands paired with their pre-denoised versions in a second step feed a Convolutional Neural Network. To network generalization, one of the inputs is the noise level of the input image, allowing a single model to work with different noise levels. This restoration technique overcomes quality when compared to current eight classical and neural methods. The results show higher peak signal to noise ratio, structural similarity index, and spectral angle mapper metrics than all the other restoration methods, surpassing those achieved using Block Matching and 4D Filtering alone. Besides, the results show a higher level of detail visually while at the same time reducing over-smoothing on the input images’ features. The paper also includes an algorithm for complete image restoration, allowing for denoising full-sized hyperspectral images independent of their shape. The dataset creation used for network training is detailed, based on a small set of available hyperspectral images, encompassing data normalization, conversion, and storage.

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]

Hyperspectral images (HSIs) denoising is a critical research area in image processing duo to its importance in improving the quality of HSIs, which has a negative impact on object detection and classification and so on. In this paper, we develop a noise reduction method based on principal component analysis (PCA) for hyperspectral imagery, which is dependent on the assumption that the noise can be removed by selecting the leading principal components. The main contribution of paper is to introduce the spectral spatial structure and nonlocal similarity of the HSIs into the PCA denoising model. PCA with spectral spatial structure can exploit spectral correlation and spatial correlation of HSI by using 3D blocks instead of 2D patches. Nonlocal similarity means the similarity between the referenced pixel and other pixels in nonlocal area, where Mahalanobis distance algorithm is used to estimate the spatial spectral similarity by calculating the distance in 3D blocks. The proposed method is tested on both simulated and real hyperspectral images, the results demonstrate that the proposed method is superior to several other popular methods in HSI denoising. [ABSTRACT FROM AUTHOR]

High spatial resolution hyperspectral images not only contain abundant radiant and spectral information, but also display rich spatial information. In this paper, we propose a multi-feature high spatial resolution hyperspectral image classification approach based on the combination of spectral information and spatial information. Three features are derived from the original high spatial resolution hyperspectral image: the spectral features that are acquired from the auto subspace partition technique and the band index technique; the texture features that are obtained from GLCM analysis of the first principal component after principal component analysis is performed on the original image; and the spatial autocorrelation features that contain spatial band X and spatial band Y, with the grey level of spatial band X changing along columns and the grey level of spatial band Y changing along rows. The three features are subsequently combined together in Support Vector Machine to classify the high spatial resolution hyperspectral image. The experiments with a high spatial resolution hyperspectral image prove that the proposed multi-feature classification approach significantly increases classification accuracies. [ABSTRACT FROM AUTHOR]

The classification of Hyperspectral Image (HSI) plays an important role in various fields. To achieve more precise multi-target classification in a short time, a method for combining discrete non-local theory with traditional variable fraction Potts models is presented in this paper. The nonlocal operator makes better use of the information in a certain region centered on that pixel. Meanwhile, adding the constraint in the model can ensure that every pixel in HSI has only one class. The proposed model has the characteristics of non-convex, nonlinear, and non-smooth so that it is difficult to achieve global optimization results. By introducing a series of auxiliary variables and using the alternating direction method of multipliers, the proposed classification model is transformed into a series of convex subproblems. Finally, we conducted comparison experiments with support vector machine (SVM), K-nearest neighbor (KNN), and convolutional neural network (CNN) on five different dimensional HSI data sets. The numerical results further illustrate that the proposed method is stable and efficient and our algorithm can get more accurate predictions in a shorter time, especially when classifying data sets with more spectral layers. [ABSTRACT FROM AUTHOR]

Now a days, Remote Sensing (RS) techniques are used for earth observation and for detection of soil types with high accuracy and better reliability. This technique provides perspective view of spatial resolution and aids in instantaneous measurement of soil's minerals and its characteristics. There are a few challenges that is present in soil classification using image enhancement such as, locating and plotting soil boundaries, slopes, hazardous areas, drainage condition, land use, vegetation etc. There are some traditional approaches which involves few drawbacks such as, manual involvement which results in inaccuracy due to human interference, time consuming, inconsistent prediction etc. To overcome these draw backs and to improve the predictive analysis of soil characteristics, we propose a Hybrid Deep Learning improved BAT optimization algorithm (HDIB) for soil classification using remote sensing hyperspectral features. In HDIB, we propose a spontaneous BAT optimization algorithm for feature extraction of both spectral-spatial features by choosing pure pixels from the Hyper Spectral (HS) image. Spectral-spatial vector as training illustrations is attained by merging spatial and spectral vector by means of priority stacking methodology. Then, a recurring Deep Learning (DL) Neural Network (NN) is used for classifying the HS images, considering the datasets of Pavia University, Salinas and Tamil Nadu Hill Scene, which in turn improves the reliability of classification. Finally, the performance of the proposed HDIB based soil classifier is compared and analyzed with existing methodologies like Single Layer Perceptron (SLP), Convolutional Neural Networks (CNN) and Deep Metric Learning (DML) and it shows an improved classification accuracy of 99.87%, 98.34% and 99.9% for Tamil Nadu Hills dataset, Pavia University and Salinas scene datasets respectively. [ABSTRACT FROM AUTHOR]

Classification of Hyperspectral images is mostly based on the spectral-spatial features in existing classification techniques. The captured Hyperspectral images from satellites may contain some noisy bands due to water absorption. The process of radiometric and atmospheric corrections leads to the removal of useful bands present in the acquired HSI. In this paper, a novel framework is proposed in which interpolation is used to accommodate the loss of noisy bands. Further, the extraction of hybrid features is performed using PCA and LPP to preserve spatial information, and these features are passed as input to the machine learning models. The proposed framework is compared with the existing spectral-spatial and spectral based frameworks by using the standard datasets-Indian Pines, Salinas, Pavia University, and Kennedy Space Centre. The accuracy of the classification is increased significantly when the proposed framework is blended with state-of-art classifiers. [ABSTRACT FROM AUTHOR]

Impervious surfaces have been widely recognized as an indicator for urbanization and environment monitoring. Plenty of methods have been proposed to extract impervious surfaces using remote sensing images. However, accurately extracting impervious surface is still a challenging task due to the confusion between impervious surface and bare soil. Thus, this paper presents a hybrid approach consisting of spectral-spatial feature sparse representation (SS-SR) and post-processing to extract urban impervious surface from hyperspectral images. We first extracted spectral and spatial features from hyperspectral images. Then, the spectral and spatial information of a pixel is represented by the vector stacking strategy. Each pixel vector can be represented by a linear combination of a few atoms from a learned dictionary, which is more suitable for impervious surface estimation. The sparse coefficients were automatically learned and then used for extracting impervious surface. The proposed impervious surface extraction method was evaluated with four hyperspectral datasets. We compared our algorithms with the state-of-the-art per-pixel based impervious surface extraction methods. The encouraging experimental results demonstrate the SS-SR algorithm generally outperforms the classic support vector machines and random forest. The improvement is more significant when combining SS-SR with post-classification approach. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) clustering is generally a challenging task because of the complex spectral-spatial structure. Based on the assumption that all the pixels are sampled from the union of subspaces, recent works have introduced a robust technique--the sparse subspace clustering (SSC) algorithm and its enhanced versions (SSC models incorporating spatial information)--to cluster HSIs, achieving excellent performances. However, these methods are all based on the linear representation model, which conflicts with the well-known nonlinear structure of HSIs and limits their performance to a large degree. In this paper, to overcome these obstacles, we present a new kernel sparse subspace clustering algorithm with a spatial max pooling operation (KSSC-SMP) for hyperspectral remote sensing data interpretation. The proposed approach maps the feature points into a much higher dimensional kernel space to extend the linear sparse subspace clustering model to nonlinear manifolds, which can better fit the complex nonlinear structure of HSIs. With the help of the kernel sparse representation, a more accurate representation coefficient matrix can be obtained. A spatial max pooling operation is utilized for the representation coefficients to generate more discriminant features by integrating the spatial-contextual information, which is essential for the accurate modeling of HSIs. This paper is an extension of our previous conference paper, and a number of enhancements are put forward. The proposed algorithm was evaluated on two well-known hyperspectral data sets--the Salinas image and the University of Pavia image--and the experimental results clearly indicate that the newly developed KSSC-SMP algorithm can obtain very competitive clustering results for HSIs, outperforming the current state-of-the-art clustering methods. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of lossy compression for hyperspectral images and presents an efficient compression algorithm based on distributed source coding. The proposed algorithm employs a block-based quantizer followed by distributed lossless coding, which is implemented through the use of multilevel coset codes. First, a bitrate allocation algorithm is proposed to assign the rational bitrate for each block. Subsequently, the multilinear regression model is employed to construct the side information of each block, and the optimal quantization step size of each block is obtained under the assigned bitrate while minimizing the distortion. Finally, the quantized version of each block is encoded by distributed lossless compression. Experimental results show that the compression performance of the proposed algorithm is competitive with that of state-of-the-art transform-based compression algorithms. Moreover, the proposed algorithm provides both low encoder complexity and error resilience, making it suitable for onboard compression. [ABSTRACT FROM AUTHOR]

Currently, hyperspectral images have potential applications in many scientific areas due to the high spectral resolution. Extracting suitable and adequate bands/features from high dimensional data is a crucial task to classify such data. To overcome this issue, dimension reduction techniques have direct effects to improve the efficiency of classifiers on hyperspectral images. One common approach for decreasing the dimensionality is the feature/band selection by considering the optimum dimensionality of the hyperspectral imagery. In this paper, a new method was proposed to select optimal band for classification application, based on a metaheuristic Invasive Weed Optimization (IWO) algorithm. In this regard, the K-nearest neighbour (K-NN) technique was used as the classifier. Moreover, as a by-product of our band selection method, a new method was proposed to estimate an optimum dimension of the reduced hyperspectral images for better classification. Experimental results over three real-world hyperspectral datasets clearly showed that the proposed IWO-based band selection algorithm of this study led to the significant progress in selecting suitable bands for classification applications and estimation of optimum dimensionality of these datasets. In this regard, the overall accuracy (OA) of classification of the proposed IWO-based band selection algorithm was 92.02, 93.57, and 89.72 % for each dataset, respectively. Moreover, results reveal the superiority of the proposed IWO-based band selection algorithm against the other algorithms including GA, SA, ACO, and PSO for band selection purpose. [ABSTRACT FROM AUTHOR]

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]

The current increase of spatial as well as spectral resolutions of modern remote sensing sensors represents a real opportunity for many practical applications but also generates important challenges in terms of image processing. In particular, the spatial correlation between pixels and/or the spectral correlation between spectral bands of a given pixel cannot be ignored. The traditional pixel-based representation of images does not facilitate the handling of these correlations. In this paper, we discuss the interest of a particular hierarchical region-based representation of images based on binary partition tree (BPT). This representation approach is very flexible as it can be applied to any type of image. Here both optical and radar images will be discussed. Moreover, once the image representation is computed, it can be used for many different applications. Filtering, segmentation, and classification will be detailed in this paper. In all cases, the interest of the BPT representation over the classical pixel-based representation will be highlighted. [ABSTRACT FROM PUBLISHER]

Exploring spatial-spectral data frequently involves classifying hyperspectral images using convolutional neural networks. Due to the high complexity of the data and the scarcity of available training samples, hyperspectral image classification presents significant difficulties. In the context of supervised classification, we find that traditional experimental designs are frequently misused in the spectral-spatial processing context, resulting in unfair or biased performance evaluation, particularly when training and testing samples are selected at random from the same dataset. Under these circumstances, the dependence caused by the overlap between training and testing samples may be artificially increased, in breach of the data independence assumption upheld by supervised learning theory. In order to prevent an unbiased classification result, we present in this paper a controlled strategy designed to minimize the overlap between the samples present in the training and the testing data sets. The proposed controlled sampling strategy ensures a more trustworthy generalization of the CNN model by minimizing the issues present in the random sampling approach, such as the inability to determine whether or not an increase in classification accuracy is due to the spatial information incorporated into a classifier or to an increase in the overlap between training and testing data sets. Experiments performed with a wavelet CNN on different HSIs, namely Indian Pines, Pavia University, and Salinas, ensure the generalization of the data under the assumption that the training and data sets are independent from one another, based on a controlled strategy. Considering the high dimension of the HSI image, as a preprocessing step, the evaluation of the proposed framework is done by PCA and FA methods. [ABSTRACT FROM AUTHOR]

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]

This paper studies a new Bayesian unmixing algorithm for hyperspectral images. Each pixel of the image is modeled as a linear combination of so-called endmembers. These endmembers are supposed to be random in order to model uncertainties regarding their knowledge. More precisely, we model endmembers as Gaussian vectors whose means have been determined using an endmember extraction algorithm such as the famous N-finder (N-FINDR) or Vertex Component Analysis (VCA) algorithms. This paper proposes to estimate the mixture coefficients (referred to as abundances) using a Bayesian algorithm. Suitable priors are assigned to the abundances in order to satisfy positivity and additivity constraints whereas conjugate priors are chosen for the remaining parameters. A hybrid Gibbs sampler is then constructed to generate abundance and variance samples distributed according to the joint posterior of the abundances and noise variances. The performance of the proposed methodology is evaluated by comparison with other unmixing algorithms on synthetic and real images. [ABSTRACT FROM AUTHOR]

The methods based on processing video data have shown their efficiency in many areas of agriculture and forestry. Nevertheless, they are not enough accurate for classification of barely discernible objects and types of plants, which can be provided only using hyperspectral sensors. However, such devices by now were expensive and difficult in operation and were used mostly on satellites and manned aircraft. In recent years, the technologies for creating smaller and lighter sensors have been proposed; these technologies are based on the choice of restricted number of spectral intervals and their position at the design stage. They may be used for scientific or commercial goals under field conditions and, in addition, installed on unmanned aerial vehicles. Exemplified by a 220-channel hyperspectral image, this paper investigates the capability of significant reduction in the amount of registered data due to choice of position and width of restricted number of most informative spectral channels in solving the classification problem of agricultural plants. It is shown that the applied method for generating feature systems has a considerable advantage against the regular decimation and is close in its efficiency to the methods based on the analysis of principal components, but has a significantly less amount of needed computations. [ABSTRACT FROM AUTHOR]

The problem of jointly segmenting objects, according to a set of labels (of cardinality L), from a set of images (of cardinality K) to produce K individual segmentations plus one joint segmentation, can be cast as a Markov random field model. Coupling terms in the considered energy function enforce the consistency between the individual segmentations and the joint segmentation. However, neither optimality on the minimizer (at least for particular cases), nor the sensitivity of the parameters, nor the robustness of this approach against standard ones has been clearly discussed before. This paper focuses on the case where L > 1 , K > 1 and the segmentation problem is handled using graph cuts. Noticeably, some properties of the considered energy function are demonstrated, such as global optimality when L = 2 and K > 1 , the link with majority voting and the link with naive Bayes segmentation. Experiments on synthetic and real images depict superior segmentation performance and better robustness against noisy observations. [ABSTRACT FROM AUTHOR]

Due to hardware limitations of the imaging sensors, it is challenging to acquire images of high resolution in both spatial and spectral domains. Fusing a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI) to obtain an HR-HSI in an unsupervised manner has drawn considerable attention. Though effective, most existing fusion methods are limited due to the use of linear parametric modeling for the spectral mixture process, and even the deep learning-based methods only focus on deterministic fully-connected networks without exploiting the spatial correlation and local spectral structures of the images. In this paper, we propose a novel variational probabilistic autoencoder framework implemented by convolutional neural networks, in order to fuse the spatial and spectral information contained in the LR-HSI and HR-MSI, called FusionNet. The FusionNet consists of a spectral generative network, a spatial-dependent prior network, and a spatial-spectral variational inference network, which are jointly optimized in an unsupervised manner, leading to an end-to-end fusion system. Further, for fast adaptation to different observation scenes, we give a meta-learning explanation to the fusion problem, and combine the FusionNet with meta-learning in a synergistic manner. Effectiveness and efficiency of the proposed method are evaluated based on several publicly available datasets, demonstrating that the proposed FusionNet outperforms the state-of-the-art fusion methods. [ABSTRACT FROM AUTHOR]

• This paper proposes a cofactorization method to perform jointly classification and representation learning. • The novel coupling approach produces a coherent and fully-interpretable hierarchical model. • The proposed model offers a rich interpretation of the data. • Performance is assessed on synthetic and real data in the specific context of hyperspectral image interpretation. Supervised classification and representation learning are two widely used classes of methods to analyze multivariate images. Although complementary, these methods have been scarcely considered jointly in a hierarchical modeling. In this paper, a method coupling these two approaches is designed using a matrix cofactorization formulation. Each task is modeled as a factorization matrix problem and a term relating both coding matrices is then introduced to drive an appropriate coupling. The link can be interpreted as a clustering operation over the low-dimensional representation vectors. The attribution vectors of the clustering are then used as features vectors for the classification task, i.e., the coding vectors of the corresponding factorization problem. A proximal gradient descent algorithm, ensuring convergence to a critical point of the objective function, is then derived to solve the resulting non-convex non-smooth optimization problem. An evaluation of the proposed method is finally conducted both on synthetic and real data in the specific context of hyperspectral image interpretation, unifying two standard analysis techniques, namely unmixing and classification. [ABSTRACT FROM AUTHOR]

Neighborhood rough sets (NRS), an extension of rough sets, are widely used for feature selection. Although NRS have the advantage of dealing with the continuous data, success of the NRS-based feature selection techniques is strongly dependent on a predefined threshold value which determines the size of neighborhood granule. In this paper, we have proposed a novel technique to detect a suitable threshold of NRS for hyperspectral band selection. Our proposed technique analyzes the changes in boundary regions to select a suitable threshold value that keeps less uncertain boundary samples into positive region and more uncertain boundary samples into boundary region of the decision attribute. The effectiveness of the proposed technique is assessed by using different data sets. [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]

Snapshot compressive imaging (SCI) refers to compressive imaging systems where multiple frames are mapped into a single measurement, with video compressive imaging and hyperspectral compressive imaging as two representative applications. Though exciting results of high-speed videos and hyperspectral images have been demonstrated, the poor reconstruction quality precludes SCI from wide applications. This paper aims to boost the reconstruction quality of SCI via exploiting the high-dimensional structure in the desired signal. We build a joint model to integrate the nonlocal self-similarity of video/hyperspectral frames and the rank minimization approach with the SCI sensing process. Following this, an alternating minimization algorithm is developed to solve this non-convex problem. We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction. Both simulation and real data (captured by four different SCI cameras) results demonstrate that our proposed algorithm leads to significant improvements compared with current state-of-the-art algorithms. We hope our results will encourage the researchers and engineers to pursue further in compressive imaging for real applications. [ABSTRACT FROM AUTHOR]

Recent advances in remote sensing have shown great potential for different kind of applications like vegetation and crop supervision. Using hyperspectral images (HSI), this process can be performed over large areas of land, allowing for a fast and non-invasive analysis of variables such as water stress, diseases, type of crops, among many others. In this context, representative spatial-spectral features are crucial to develop the data classification process of hyperspectral remote sensing images. In this way, the use of deep learning networks has shown a remarkable classification performance in many applications as the processing of hyperspectral images. In this paper, a data classification model that use kernel PCA (K-PCA) and inception network architecture to generate deep spatial-spectral features is proposed. The features generated are used to label the different kind of classes into the HSI. The labeling process uses a logistic regression (LR) algorithm. This model was validated using six different datasets. The experiments performed shown that the proposed strategy allows improving the data classification performance regarding the results obtained by the traditional stacked layer model of convolutional neural networks (CNN). Quantitatively speaking, the overall accuracy over all experiments of the proposed model for all tested datasets is greater than 92%. [ABSTRACT FROM AUTHOR]

With the rapid development of hyperspectral remote sensing technology, the spatial resolution and spectral resolution of hyperspectral images are continually increasing, resulting in a continual increase in the scale of hyperspectral data. At present, hyperspectral lossless compression technology has reached a bottleneck. Simultaneously, the rise of deep learning has provided us with new ideas. Therefore, this paper examines the use of deep learning for the lossless compression of hyperspectral images. In view of the differential pulse code modulation (DPCM) method being insufficient for predicting spectral band information, the proposed method, called C-DPCM-RNN, uses a deep recurrent neural network (RNN) to improve the traditional DPCM method and improve the generalization ability and prediction accuracy of the model. The final experimental result shows that C-DPCM-RNN achieves better compression on a set of calibrated AVIRIS test images provided by the Multispectral and Hyperspectral Data Compression Working Group of the Consultative Committee for Space Data Systems in 2006. C-DPCM-RNN overcomes the limits of traditional methods in its performance on uncalibrated AVIRIS test images. [ABSTRACT FROM AUTHOR]