A Novel Spatial-Spectral Framework for the Classification of Hyperspectral Satellite Imagery

TL;DR

This paper introduces a new spatial-spectral framework for hyperspectral satellite image classification that combines spectral analysis with spatial context, achieving high accuracy and computational efficiency.

Contribution

The paper presents a novel framework integrating spectral and spatial information using GML and CNN methods with watershed segmentation, outperforming previous approaches.

Findings

Achieved 99.52% accuracy on Pavia University dataset.

Achieved 98.31% accuracy on Indian Pines dataset.

GML approach performs comparably to deep learning methods.

Abstract

Hyper-spectral satellite imagery is now widely being used for accurate disaster prediction and terrain feature classification. However, in such classification tasks, most of the present approaches use only the spectral information contained in the images. Therefore, in this paper, we present a novel framework that takes into account both the spectral and spatial information contained in the data for land cover classification. For this purpose, we use the Gaussian Maximum Likelihood (GML) and Convolutional Neural Network methods for the pixel-wise spectral classification and then, using segmentation maps generated by the Watershed algorithm, we incorporate the spatial contextual information into our model with a modified majority vote technique. The experimental analyses on two benchmark datasets demonstrate that our proposed methodology performs better than the earlier approaches by achieving an accuracy of 99.52% and 98.31% on the Pavia University and the Indian Pines datasets respectively. Additionally, our GML based approach, a non-deep learning algorithm, shows comparable performance to the state-of-the-art deep learning techniques, which indicates the importance of the proposed approach for performing a computationally efficient classification of hyper-spectral imagery.