Superpixel-Based Singular Spectrum Analysis for Effective Spatial-Spectral Feature Extraction

Abstract

In the processing of remotely sensed data, classification may be preceded by feature extraction, which helps in making the most informative parts of the data emerge. Effective feature extraction may boost the efficiency and accuracy of the following classification, and hence various methods have been proposed to perform it. Recently, Singular Spectrum Analysis (SSA) and its 2-D variation (2D-SSA) have emerged as popular, cutting-edge technologies for effective feature extraction in Hyperspectral Images (HSI). Using 2D-SSA, each band image of an HSI is initially decomposed into various components, and then the image is reconstructed using the most significant eigen-tuples relative to their eigen-values, which represent strong spatial features for the classification task. However, instead of performing reconstruction on the whole image, it may be more effective to apply reconstruction to object-specific spatial regions, which is the proposed objective of this research. As an HSI may cover a large area, multiple objects are generally present within a single scene. Hence, spatial information can be highlighted accurately by specializing the reconstruction based on the local context. The local context may be defined by the so-called superpixels, i.e., finite sets of pixels that constitute a homogeneous set. Each superpixel may undergo tailored reconstruction, with a process expected to perform better than non-spatially-adaptive approaches. In this paper, a Superpixel-based SSA (SP-SSA) method is proposed where the image is first segmented into multiple regions using a superpixel segmentation approach. Next, each segment is individually reconstructed using 2D-SSA. In doing so, the spatial contextual information is preserved, leading to better classifier performance. The performance of the reconstructed features is evaluated using an SVM classifier. Experiments on four popular benchmark datasets reveal that, in terms of the classification accuracy, the proposed approach overperforms the standard SSA technique and various common spatio-spectral classification methods.

Two-dimensional compact variational mode decomposition for effective feature extraction and data classification in hyperspectral imaging

“…Extracting local features instead of global features, especially in HSIs, can be more effectively describe the objects in the image. Based on the combination of superpixel segmentation and 2-D-SSA, 39 the superpixel adaptive SSA is proposed, 40 which makes full use of the local spatial information of HSI instead of the global information. By combining superpixel with intrinsic image decomposition, 41 we can embed the superpixel feature in 2-D-C-VMD methods.…”

Hyperspectral Band Selections for Enhancing the Discrimination of Difficult Targets Using Local Band Index and Particle Swarm Optimization

“…Local featurebased manifold learning [9,10] and sparse representation [11] are also important hyperspectral feature extraction methods. At the same time, feature extraction can also combine two different features of space and spectrum for DR [12]. FE is the goal of reducing dimensionality from a mathematical point of view, but while reducing the dimensionality, it also loses the physical information of ground objects, radiations or reflections contained in the original band.…”

Spatial Analysis for Landscape Changes

“…Subudhi et al (2021) [5] propose a new method of image segmentation of hyperspectral satellite images (i.e., the Superpixel-based SSA, SP-SSA), which can provide an improvement to the capturing of object-specific spatio-spectral information. The performance of the method is evaluated using an SVM classifier, suggesting that the proposed approach overperforms the standard SSA technique and various common spatio-spectral classification methods, in terms of classification accuracy.…”