Manifold learning based feature extraction for classification of hyper-spectral data

Abstract

Advances in hyperspectral sensing provide new capability for characterizing spectral signatures in a wide range of physical and biological systems, while inspiring new methods for extracting information from these data. Hyperspectral image data often lie on sparse, nonlinear manifolds whose geometric and topological structures can be exploited via manifold learning techniques. In this article, we focused on demonstrating the opportunities provided by manifold learning for classification of remotely sensed data. Challenges and opportunities remain for future research in manifold learning, including joint exploitation of advantages of global and local structures in dynamic, multi-temporal environments, multiscale manifolds, and integration with semi-supervised and active learning.