Hyperspectral image classification using graph-based wavelet transform

Abstract. Hyperspectral images (HSIs) contain hundreds of spectral bands, providing high-resolution spectral information pertaining to the Earth’s surface. Additionally, abundant spatial contextual information can also be obtained simultaneously from a HSI. To characterize the properties of ground objects, classification is the most widely-used technology in the field of remote sensing, where each pixel in a HSI is assigned to a pre-defined class. Over the past decade, deep learning has attracted increasing attention in the machine-learning and computer-vision domains, due to its favourable performances for various types of tasks, and it has been successfully introduced to the remote-sensing community. Instead of utilizing the shallow features within in a given image, which is the approach that is generally adopted in other conventional classification methods, deep-learning algorithms can extract hierarchical features from raw HSI data. Within the deep-learning framework, recurrent neural networks (RNNs), which are able to encode sequential features, have exhibited promising capabilities and have achieved encouraging performances, especially for the natural-language processing and speech-recognition communities. As multi-temporal remote-sensing images can be readily obtained from increasing numbers of satellite and unmanned aircraft systems, and since analysis of such multi-temporal data comprises a critical issue within numerous research subfields, including land-cover and land-change analyses, and land-resource management, RNNs have been applied in recent studies in order to extract temporal sequential features from multi-temporal remote-sensing images for the purpose of image classification. Apart from using multi-temporal image datasets, RNNs can also be utilized on a single image, where the spectral feature/band of each individual pixel can be taken as a sequential feature for the input layer of RNNs. However, the application of such sequential feature extraction that relies on a single image still needs to be further investigated since applying RNNs to spectral bands will directly introduce more parameters that need to be optimized, consequently increasing the total training time.In this study, we propose a novel RNN-based HSI classification framework. In this framework, unlabelled pixels obtained from a single image are considered when constructing sequential features. Two spatial similarity measurements, referred to as pixel-matching and block-matching, respectively, are employed to extract pixels that are “similar” to the target pixel. Then, the sequential feature of the target pixel is constructed by exploiting several of the most “similar” pixels and ordering them based on their similarities to the target pixel. The aforementioned two schemes are advantageous, as unlabelled pixels within the given HSI are taken into consideration for similarity measurement and sequential feature construction for the RNN model. Moreover, the block-matching scheme also takes advantage of spatial contextual information, which has been widely utilized in spatial-spectral-based HSI classification methods. To evaluate the proposed methods, two benchmark HSIs are used, including a HSI collected over Pavia University, Italy by the airborne Reflective Optics System Imaging Spectrometer (ROSIS) sensor, and an image acquired over the Salinas Valley, California, USA via the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. Spatio-temporally coincident ground-reference data accompanies each of these respective HSIs. In addition, the proposed methods are compared with three state-of-the-art algorithms, including support vector machine (SVM), the 1-dimensional convolutional neural network (1DCNN), and the 1-dimensional RNN (1DRNN).Experimental results indicate that our proposed methods achieve markedly better classification performance compared with the baseline algorithms on both datasets. For example, for the Pavia University image, the block-matching based RNN achieves the highest overall classification accuracy, with 94.32% accuracy, which is 9.87% higher than the next most accurate algorithm of the aforementioned three baseline methods, which in this case is the 1DCNN, with 84.45% overall accuracy. More specifically, the block-matching method performs better than the pixel-matching method in terms of both quantitative and qualitative assessments. Based on visual assessment/interpretation of the classification maps, it is apparent that “salt-and-pepper” noise is markedly alleviated; with block-matching, smoother classified images are generated compared with pixel-matching-based methods and the three baseline algorithms. Such results demonstrate the effectiveness of utilizing spatial contextual information in the similarity measurement.

Hyperspectral remote sensing offers a powerful tool in many different application contexts. The imbalance between the high dimensionality of the data and the limited availability of training samples calls for the need to perform dimensionality reduction in practice. Among traditional dimensionality reduction techniques, feature extraction is one of the most widely used approaches due to its flexibility to transform the original spectral information into a subspace. In turn, band selection is important when the application requires preserving the original spectral information (especially the physically meaningful information) for the interpretation of the hyperspectral scene. In the case of hyperspectral image classification, both techniques need to discard most of the original features/bands in order to perform the classification using a feature set with much lower dimensionality. However, the discriminative information that allows a classifier to provide good performance is usually classdependent and the relevant information may live in weak features/bands that are usually discarded or lost through subspace transformation or band selection. As a result, in practice, it is challenging to use either feature extraction or band selection for classification purposes. Relevant lines of attack to address this problem have focused on multiple feature selection aiming at a suitable fusion of diverse features in order to provide relevant information to the classifier. In this paper, we present a new dimensionality reduction technique, called multiple criteria-based spectral partitioning, which is embedded in an ensemble learning framework to perform advanced hyperspectral image classification. Driven by the use of a multiple band priority criteria that is derived from classic band selection techniques, we obtain multiple spectral partitions from the original hyperspectral data that correspond to several band subgroups with much lower spectral dimensionality as compared with the original band set. An ensemble learning technique is then used to fuse the information from multiple features, taking advantage of the relevant information provided by each classifier. Our experimental results with two real hyperspectral images, collected by the reflective optics system imaging spectrometer (ROSIS) over the University of Pavia in Italy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) over the Salinas scene, reveal that our presented method, driven by multiple band priority criteria, is able to obtain better classification results compared with classic band selection techniques. This paper also discusses several possibilities for computationally efficient implementation of the proposed technique using various high-performance computing architectures.

Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.

In recent studies, superpixel segmentation has been integrated into hyperspectral (HS) image classification methods. However, the existing superpixel-based classification methods usually suffer from two serious problems. First, the accuracy and efficiency of current superpixel segmentation approaches cannot meet the demands of practical applications for HS images; second, conventional superpixel-based classification methods generally consider each generated superpixel as a unit for the image classification, which may help to reduce the computing time but result in a significant decrease of the classification accuracy. To solve the problems, we propose a fast region growing based superpixel segmentation (FRGSS) algorithm and a novel texture-adaptive superpixel integration strategy (TASIS) for the HS image classification. Experimental results on real Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) HS images demonstrate that the proposed FRGSS outperforms the state-of-the-art superpixel algorithm. In addition, the superiority of the TASIS is verified compared to the pixel-wise and the conventional superpixel-based classification methods.

The support vector machine (SVM) has been a dominant machine-learning technique in the last decade and has demonstrated its efficiency in many applications. Research on classification of hyperspectral images have shown the efficiency of this method to overcome the Hughes phenomenon for classification of such images. A major drawback of classification by SVM is that this classifier was originally developed to solve binary problems, and the algorithms for multiclass problems usually have a high-computational load. In this article, a new and fast method for multiclass problems is proposed. This method has two stages. In the first stage, samples are classified by a maximum likelihood (ML) classifier, and in the second stage, SVM selects the final label of a sample among high-probability classes for that sample by a tree structure. So, for each sample, only some classes must be searched by SVM to find its label. The uncertainty of ML classification for a sample is obtained by the entropy of probabilities, and the number of classes that must be searched by SVM for a sample is obtained based on the uncertainty of that sample in the primary ML classification. This approach is compared with two widely used multiclass algorithms: one-against-one (OAO) and directed acyclic graph (DAGSVM). The obtained results on real data from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) revealed less computational time and better accuracy compared to these multiclass algorithms.

Hyperspectral imaging provides detailed spectral and spatial information from the land cover that enables a precise differentiation between various surface materials. On the other hand, the performance of traditional and widely used statistical classification methods is often limited in this context, and thus alternative methods are required. In the study presented here, the performance of two machine-learning techniques, namely support vector machines (SVMs) and random forests (RFs), is investigated and the classification results are compared with those from well-known methods (i.e., maximum likelihood classifier and spectral angle mapper). The classifiers are applied to an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) dataset that was acquired near the Hekla volcano in Iceland. The results clearly show the advantages of the two proposed classifier algorithms in terms of accuracy. They significantly outperform the other methods and achieve overall accuracies of approximately 90%. Although SVM and RF show some diversity in the classification results, the global performance of the two classifiers is very similar. Thus, both methods can be considered attractive for the classification of hyperspectral data.

This study is focused on time optimization for the classification problem presenting a comparison of five Artificial Neural Network Multilayer Perceptron (ANN-MLP) architectures. We use the Artificial Neural Network (ANN) because it allows to recognize patterns in data in a lower time rate. Time and classification accuracy are taken into account together for the comparison. According to time comparison, two paradigms in the computational field for each ANN-MLP architecture are analysed with three schemes. Firstly, sequential programming is applied by using a single CPU core. Secondly, parallel programming is employed over a multi-core CPU architecture. Finally, a programming model running on GPU architecture is implemented. Furthermore, the classification accuracy is compared between the proposed five ANN-MLP architectures and a state-of.the-art Support Vector Machine (SVM) with three classification frames: 50%,60% and 70% of the data set's observations are randomly selected to train the classifiers. Also, a visual comparison of the classified results is presented. The Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) criteria are also calculated to characterise visual perception. The images employed were acquired by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), the Reflective Optics System Imaging Spectrometer (ROSIS) and the Hyperion sensor.

On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral images

Remotely sensed hyperspectral imaging allows for the detailed analysis of the surface of the Earth using advanced imaging instruments which can produce high-dimensional images with hundreds of spectral bands. Supervised hyperspectral image classification is a difficult task due to the unbalance between the high dimensionality of the data and the limited availability of labeled training samples in real analysis scenarios. While the collection of labeled samples is generally difficult, expensive, and time-consuming, unlabeled samples can be generated in a much easier way. This observation has fostered the idea of adopting semisupervised learning techniques in hyperspectral image classification. The main assumption of such techniques is that the new (unlabeled) training samples can be obtained from a (limited) set of available labeled samples without significant effort/cost. In this paper, we develop a new approach for semisupervised learning which adapts available active learning methods (in which a trained expert actively selects unlabeled samples) to a self-learning framework in which the machine learning algorithm itself selects the most useful and informative unlabeled samples for classification purposes. In this way, the labels of the selected pixels are estimated by the classifier itself, with the advantage that no extra cost is required for labeling the selected pixels using this machine–machine framework when compared with traditional machine–human active learning. The proposed approach is illustrated with two different classifiers: multinomial logistic regression and a probabilistic pixelwise support vector machine. Our experimental results with real hyperspectral images collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory's Airborne Visible–Infrared Imaging Spectrometer and the Reflective Optics Spectrographic Imaging System indicate that the use of self-learning represents an effective and promising strategy in the context of hyperspectral image classification.

Extreme learning machine (ELM) has attracted attentions in pattern recognition field due to its remarkable advantages such as fast operation, straightforward solution, and strong generalization. However, the performance of ELM for high-dimensional data, such as hyperspectral image, is still an open problem. Therefore, in this paper, we introduce ELM for hyperspectral image classification. Furthermore, in order to overcome the drawbacks of ELM caused by the randomness of input weights and bias, two new algorithms of ensemble extreme learning machines (Bagging-based and AdaBoost-based ELMs) are proposed for the classification task. In order to illustrate the performance of the proposed algorithms, support vector machines (SVMs) are used for evaluation and comparison. Experimental results with real hyperspectral images collected by reflective optics spectrographic image system (ROSIS) and airborne visible/infrared imaging spectrometer (AVIRIS) indicate that the proposed ensemble algorithms produce excellent classification performance in different scenarios with respect to spectral and spectral–spatial feature sets.

In hyperspectral images (HSI) classification, it is important to combine multiple features of a certain pixel in both spatial and spectral domains to improve the classification accuracy. To achieve this goal, this article proposes a novel spatial-spectral feature dimensionality reduction algorithm based on manifold learning. For each feature, a graph Laplacian matrix is constructed based on discriminative information from training samples, and then the graph Laplacian matrices of the various features are linearly combined using a set of empirically defined weights. Finally, the feature mapping is obtained by an eigen-decomposition problem. Based on the classification results of the public Indiana Airborne Visible Infrared Imaging Spectrometer dataset and Texas Hyperspectral Digital Imagery Collection Experiment data set, the technical accuracies show that our method achieves superior performance compared to some representative HSI feature extraction and dimensionality reduction algorithms.

Hyperspectral Image (HSI) classification plays a key role remote sensing field. Recently, deep learning has demonstrated its effectiveness in HSI Classification field. This paper presents a spectral-spatial HSI classification technique established on the deep learning based deep belief network (DBN) for deep and abstract feature extraction and adaptive boundary adjustment based segmentation. Proposed approach focuses on integrating the deep learning based spectral features and segmentation based spatial features into a framework for improved performance. Specifically, first the deep DBN model is exploited as a spectral feature extraction based classifier to extract the deep spectral features. Second, spatial contextual features are obtained by utilizing effective adaptive boundary adjustment based segmentation technique. Finally, maximum voting based criteria is operated to integrate the results of extracted spectral and spatial information for improved HSI classification. In general, exploiting spectral features from DBN process and spatial features from segmentation and integration of spectral and spatial information by maximum voting based criteria, has a substantial effect on the performance of HSI classification. Experimental performance on real and widely used hyperspectral data sets with different contexts and resolutions demonstrates the accuracy of the proposed technique and performance is comparable to several recently proposed HSI classification techniques.

Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectral remote sensing image classification

Hyperspectral image (HSI) classification has many applications in different diverse research fields. We propose a method for HSI classification using principal component analysis (PCA), 2D spatial convolution, and support vector machine (SVM). Our method takes advantage of correlation in both spatial and spectral domains in an HSI data cube at the same time. We use PCA to reduce the dimensionality of an HSI data cube. We then perform spatial convolution to the dimension-reduced data cube once and then to the convolved data cube for the second time. As a result, we have generated two convolved PCA output data cubes in a multiresolution way. We feed the two convolved data cubes to SVM to classify each pixel to one of the known classes. Experiments on three widely used hyperspectral data cubes (i.e., Indian Pines, Pavia University, and Salinas) demonstrate that our method can improve the classification accuracy significantly when compared to a few existing methods. Our method is relatively fast in terms of central processing unit computational time as well.

An orthogonal subspace projection (OSP) method using linear mixture modeling was recently explored in hyperspectral image classification and has shown promise in signature detection, discrimination, and classification. In this paper, the OSP is revisited and extended by three unconstrained least squares subspace projection approaches, called signature space OSP, target signature space OSP, and oblique subspace projection, where the abundances of spectral signatures are not known a priori but need to be estimated, a situation to which the OSP cannot be directly applied. The proposed three subspace projection methods can be used not only to estimate signature abundance, but also to classify a target signature at subpixel scale so as to achieve subpixel detection. As a result, they can be viewed as a posteriori OSP as opposed to OSP, which can be thought of as a priori OSP. In order to evaluate these three approaches, their associated least squares estimation errors are cast as a signal detection problem ill the framework of the Neyman-Pearson detection theory so that the effectiveness of their generated classifiers can be measured by receiver operating characteristics (ROC) analysis. All results are demonstrated by computer simulations and Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data.