Hyperspectral Chemical Plume Detection Algorithms Based On Multidimensional Iterative Filtering Decomposition

TL;DR

This paper introduces a novel, adaptive post-processing tool based on Multidimensional Iterative Filtering to improve chemical plume detection in hyperspectral images, enhancing classification accuracy and boundary delineation.

Contribution

It presents a new data-driven preprocessing and post-processing framework using MIF for hyperspectral chemical plume detection, outperforming traditional methods like cosine similarity.

Findings

Enhanced boundary detection accuracy in hyperspectral images.

Preprocessing with MIF improves classifier performance.

Cosine similarity outperforms in the proposed framework.

Abstract

Chemicals released in the air can be extremely dangerous for human beings and the environment. Hyperspectral images can be used to identify chemical plumes, however the task can be extremely challenging. Assuming we know a priori that some chemical plume, with a known frequency spectrum, has been photographed using a hyperspectral sensor, we can use standard techniques like the so called matched filter or adaptive cosine estimator, plus a properly chosen threshold value, to identify the position of the chemical plume. However, due to noise and sensors fault, the accurate identification of chemical pixels is not easy even in this apparently simple situation. In this paper we present a post-processing tool that, in a completely adaptive and data driven fashion, allows to improve the performance of any classification methods in identifying the boundaries of a plume. This is done using the Multidimensional Iterative Filtering (MIF) algorithm (arXiv:1411.6051, arXiv:1507.07173), which is a non-stationary signal decomposition method like the pioneering Empirical Mode Decomposition (EMD) method. Moreover, based on the MIF technique, we propose also a pre-processing method that allows to decorrelate and mean-center a hyperspectral dataset. The Cosine Similarity measure, which often fails in practice, appears to become a successful and outperforming classifier when equipped with such pre-processing method. We show some examples of the proposed methods when applied to real life problems.