Analysis of Hyperspectral Data by Means of Transport Models and Machine Learning

Abstract

We present a new physics-inspired method for analysis of hyperspectral imagery (HSI). The method is based on the concept of transport models for graphs. The proposed approach generalizes existing dimension reduction and feature extraction algorithms, by replacing the role of diffusion processes, as a measure of estimating proximity, with dynamical systems. This approach allows us to exploit different and new relationships within the complex data structures, such as those arising in HSI. We demonstrate this by proposing a specific multi-scale algorithm in which transport models are used to translate the information about contextual similarities of material classes to enhance feature extraction and classification results. This point is illustrated with a series of computational experiments.