Hyperspectral remote sensing technology has advanced significantly in the past two decades. Current sensors onboard airborne and spaceborne platforms cover large areas of the Earth surface with unprecedented spectral, spatial, and temporal resolutions. These characteristics enable a myriad of applications requiring fine identification of materials or estimation of physical parameters. Very often, these applications rely on sophisticated and complex data analysis methods. The sources of difficulties are, namely, the high dimensionality and size of the hyperspectral data, the spectral mixing (linear and nonlinear), and the degradation mechanisms associated to the measurement process such as noise and atmospheric effects. This paper presents a tutorial/overview cross section of some relevant hyperspectral data analysis methods and algorithms, organized in six main topics: data fusion, unmixing, classification, target detection, physical parameter retrieval, and fast computing. In all topics, we describe the state-of-the-art, provide illustrative examples, and point to future challenges and research directions.

/pdf/hyperspectral-remote-sensing-data-analysis-and-future-1cxk3zgg98.pdf

Hyperspectral Remote Sensing Data Analysis and Future Challenges

Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes characteristics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.

/pdf/advances-in-spectral-spatial-classification-of-hyperspectral-vlt2ik4ef1.pdf

Advances in Spectral-Spatial Classification of Hyperspectral Images

Support vector machines (SVMs) have considerable potential as classifiers of remotely sensed data. A constraint on their application in remote sensing has been their binary nature, requiring multiclass classifications to be based upon a large number of binary analyses. Here, an approach for multiclass classification of airborne sensor data by a single SVM analysis is evaluated against a series of classifiers that are widely used in remote sensing, with particular regard to the effect of training set size on classification accuracy. In addition to the SVM, the same datasets were classified using a discriminant analysis, decision tree, and multilayer perceptron neural network. The accuracy statements of the classifications derived from the different classifiers were compared in a statistically rigorous fashion that accommodated for the related nature of the samples used in the analyses. For each classification technique, accuracy was positively related with the size of the training set. In general, the most accurate classifications were derived from the SVM approach, and with the largest training set the SVM classification was significantly (p 90% correct, the classifiers differed in the ability to correctly label individual cases and so may be suitable candidates for an ensemble-based approach to classification.

/pdf/a-relative-evaluation-of-multiclass-image-classification-by-cxhcuggzt4.pdf

A relative evaluation of multiclass image classification by support vector machines

The technological evolution of optical sensors over the last few decades has provided remote sensing analysts with rich spatial, spectral, and temporal information. In particular, the increase in spectral resolution of hyperspectral images (HSIs) and infrared sounders opens the doors to new application domains and poses new methodological challenges in data analysis. HSIs allow the characterization of objects of interest (e.g., land-cover classes) with unprecedented accuracy, and keeps inventories up to date. Improvements in spectral resolution have called for advances in signal processing and exploitation algorithms. This article focuses on the challenging problem of hyperspectral image classification, which has recently gained in popularity and attracted the interest of other scientific disciplines such as machine learning, image processing, and computer vision. In the remote sensing community, the term classification is used to denote the process that assigns single pixels to a set of classes, while the term segmentation is used for methods aggregating pixels into objects and then assigned to a class.

Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods

Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification due to their ability to capture spatial–spectral feature representations. Nevertheless, their ability in modeling relations between the samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or nongrid) data representation and analysis. In this article, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new minibatch GCN (called miniGCN hereinafter), which allows to train large-scale GCNs in a minibatch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without retraining networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batchwise network training (enabling the combination of CNNs and GCNs), we explore three fusion strategies: additive fusion, elementwise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS data sets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regard to the single CNN or GCN models. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_GCN for the sake of reproducibility.

Graph Convolutional Networks for Hyperspectral Image Classification

Morphological attribute profiles (APs) are defined as a generalization of the recently proposed morphological profiles (MPs). APs provide a multilevel characterization of an image created by the sequential application of morphological attribute filters that can be used to model different kinds of the structural information. According to the type of the attributes considered in the morphological attribute transformation, different parametric features can be modeled. The generation of APs, thanks to an efficient implementation, strongly reduces the computational load required for the computation of conventional MPs. Moreover, the characterization of the image with different attributes leads to a more complete description of the scene and to a more accurate modeling of the spatial information than with the use of conventional morphological filters based on a predefined structuring element. Here, the features extracted by the proposed operators were used for the classification of two very high resolution panchromatic images acquired by Quickbird on the city of Trento, Italy. The experimental analysis proved the usefulness of APs in modeling the spatial information present in the images. The classification maps obtained by considering different APs result in a better description of the scene (both in terms of thematic and geometric accuracy) than those obtained with an MP.

Morphological Attribute Profiles for the Analysis of Very High Resolution Images

Decision level fusion has shown great potential to increase classification accuracy beyond the level reached by individual classifiers. A considerable body of literature exists on identifying optimal ways to combine classifiers. However, the selection of the classifiers to be combined is equally, if not more, crucial if an improvement is to be made for certain classifier combination schemes. Agreement among classifiers can inhibit the gains obtained regardless of the method used to combine them. The level of agreement between different classifiers used in remote sensing is assessed based on statistical measures. A study is performed in which an image is classified by several methods with different degrees of agreement between them. The results are then combined using decision fusion schemes and the increase of accuracy is observed for each combination of the individual classifications.

The effect of classifier agreement on the accuracy of the combined classifier in decision level fusion

Two wavelet transformations are used for speckle reduction and enhancement of synthetic aperture radar (SAR) images. First, a discrete wavelet transformation (DWT) based on oversampled filter banks is used. The oversampled DWT is called a double-density DWT (DD-DWT) and is based on a single-scaling function (low pass) and two distinct wavelet functions (high pass). Second, a discrete wavelet transformation based on two dual real wavelet trees is applied. Each tree produces a set of real DWTs, which together form the complex wavelet transformation (CWT), i.e., a transformation with both real and imaginary parts. Both of these DWTs are almost translation invariant and are useful for speckle reduction through their subband images, and the speckle reduction is obtained by thresholding the subband image coefficients of the digitized SAR images. A thresholding method based on the use of nonlinear functions, which are adapted for each selected subband, is used. The nonlinear functions are based on sigmoid functions. The denoising method presented shows great promise for speckle removal and, hence, can provide good detection performance for SAR-based recognition.

J. Atli Benediktsson

Papers

Morphological Attribute Profiles for the Analysis of Very High Resolution Images

The effect of classifier agreement on the accuracy of the combined classifier in decision level fusion

Almost translation invariant wavelet transformations for speckle reduction of SAR images