Hyperspectral unmixing improves identifying materials in variable lighting
Hyperspectral Unmixing using a Structured Linear Mixing Model with Additive Spectral Variability
Computer Vision and Pattern Recognition
Summary
Hyperspectral images capture detailed color information to identify materials in a scene. But these images can be tricky because the colors of materials often change due to lighting or atmospheric effects. The authors propose new methods to better uncover the true material colors and amounts present, even when these color changes happen. They include extra terms in their model to handle this variability and create algorithms that work well on both simulated and real data.
What this means in practice
- •For remote sensing analysts: Improve identification of materials in satellite images affected by lighting and atmospheric changes using the new unmixing algorithms.
- •For environmental monitoring teams: Better map land cover composition when spectral variability is present, aiding environmental assessments under varying conditions.
Authors
Salah Eddine Brezini, Yannick Deville, Moussa Sofiane Karoui, Fatima Zohra Benhalouche, Abdelaziz Ouamri
Abstract
Linear hyperspectral unmixing aims at retrieving pure material spectra present in an observed scene and their associated abundance fractions in each pixel. In most practical situations, hyperspectral images are affected by spectral variability (SV) also known as intra-class variability, which is caused by different physical phenomena including atmospheric effects, intrinsic variability of the pure materials and illumination or topographic changes. Nevertheless, the standard hyperspectral unmixing methods that rely on the Linear Mixing Model (LMM) do not consider these phenomena. Thus, neglecting them will spread errors throughout the linear hyperspectral unmixing process. To avoid this problem, this paper proposes two hyperspectral unmixing algorithms dedicated to a parametric model called Structured Additive Variability LMM (SAV-LMM). This mixing model handles SV in an additive manner by incorporating two terms into the standard LMM. Moreover, the designed algorithms are based on Nonnegative Matrix Factorization (NMF) and optimize a cost function which integrates additional penalization accounting for SV. Furthermore, a novel improved initialization scheme, which takes SV into account, is proposed. Experiments conducted on both synthetic and real datasets show the effectiveness of the proposed algorithms for linearly unmixing hyperspectral images with SV compared to the tested state-of-the-art methods.