Spectral-spatial Framework Research Articles

Global Spatial and Local Spectral Similarity-Based Manifold Learning Group Sparse Representation for Hyperspectral Imagery Classification

Spectral–spatial framework has been widely applied for hyperspectral image classification task. Some well-established models, such as group sparse representation (GSR), have gained a certain advance but still mainly focus on the usage of local spatial similarity and neglect the nonlocal spatial information. Recently, nonlocal self-similarity (NLSS) has been exploited to support the spatial coherence tasks. However, current NLSS-based methods are biased toward the direct use of nonlocal spatial information as a whole, while the underlying spectral information is not well exploited. In this article, we proposed a novel method to exploit local spectral similarity through nonlocal spatial similarity, with the integration of local spatial consistency in a single framework. Specifically, the proposed approach first exploits the NLSS by searching the nonoverlapped similar patches in defined scopes. Then, spectral similarity is determined locally within the found patches. After that, the found similar data and the original data are fused in a designed pattern. Finally, the GSR-based classifier (GSRC) is applied to process the fused data characterized by the manifold learning algorithm. The experimental results based on three real hyperspectral data sets demonstrate the efficiency of the proposed method, with improvements over the other related nonlocal or local similarity-based methods.

Supervised Functional Data Discriminant Analysis for Hyperspectral Image Classification

This article proposes a functional data discriminant analysis (FDDA) method for hyperspectral image (HSI) classification. This method analyzes and processes the HSI data from a functional point of view, which is a novel perspective in HSI processing. The classical methods achieve dimensionality reduction by directly eliminating the redundancy of the HSI data. However, the proposed method extracts the functional features by utilizing the redundancy of the HSI data. Functional features can effectively reveal inherent characteristics of the HSI data with the change in the wavelengths. Based on this, a regularized weighted fitting model is first built for converting a spectral vector into a spectral curve. Second, an FDDA method defined in the function field is presented for extracting the functional features of the spectral curves. Finally, a novel spectral-spatial framework is designed for classification tasks of HSI data sets. Experimental results in three commonly used HSI data sets indicate that the proposed method is effective and leads to promising classification results compared with some benchmarking methods. More importantly, the work tries to diversify and develop the existing theory and methods of HSI classification from discrete (vector) data learning methods to continuous (functional) data learning methods.

Kernel Composition with the one-against-one Cascade for Integrating External Knowledge into SVM Classification

Summary: This work focuses on two main questions. How can data fusion be performed before SVM (support vector machine) classi›cation? And secondly: how can the one-against-one cascade be exploited to use information selectively thus integrating human knowledge? Kernel composition represents a specialized method for fusing data on the feature level. Its main advantage is given by the fact that it reduces the Hughes phenomenon (performance decrease due to high dimensionality) because it abstains from raising dimensionality in the feature space. Since the paper focuses on hyperspectral data, a specialized kernel based on the spectral angle is employed and evaluated. Two application schemes are presented. At ›rst, hyperspectral data are fused with laserscanning data by taking into account explicit knowledge on roof geometries. Secondly, a spectral-spatial framework forhyperspectraldataispresentedwhichintegrates implicit knowledge on the relevance of spatial context into classi›cation. Both approaches are promising as they obtain higher classi›cation accuracies when integrating external knowledge. The innovation of the contribution is that data fusion with a second source of data via kernel composition is combined with a modi›cation of the one-againstone cascade which allows integration of human