Developing Spectral Libraries Using Multiple Target Multiple Instance Adaptive Cosine/Coherence Estimator

Meerdink, Susan; Bocinsky, James; Wetherley, Erin B.; Zare, Alina; McCurley, Connor H.; Gader, Paul D.

doi:10.1109/whispers.2019.8920989

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image pixels are included in the library either based on their correlation to some initial endmembers manually selected as the extreme points of the PCA of the HI [95], [238], or simply by manually screening a large number of pure pixels extracted from the HI using expert knowledge about the spectral characteristic of the materials in the scene [239]. Other work used only partially labeled data in order to reduce the amount of domain knowledge that is required [240]. Recent strategies attempted to automate this process by extending EEAs for the extraction of multiple signatures of each material in the observed HI.…”

Section: Spectral Librariesmentioning

confidence: 99%

Spectral Variability in Hyperspectral Data Unmixing: A comprehensive review

Borsoi

Imbiriba

Bermudez

et al. 2021

IEEE Geosci. Remote Sens. Mag.

Self Cite

143

View full text Add to dashboard Cite

The spectral signatures of the materials contained in hyperspectral images (HI), also called endmembers (EM), can be significantly affected by variations in atmospheric, illumination or environmental conditions typically occurring within an HI. Traditional spectral unmixing (SU) algorithms neglect the spectral variability of the endmembers, what propagates significant mismodeling errors throughout the whole unmixing process and compromises the quality of its results. Therefore, large efforts have been recently dedicated to mitigate the effects of spectral variability in SU. This resulted in the development of algorithms that incorporate different strategies to allow the EMs to vary within an HI, using, for instance, sets of spectral signatures known a priori, Bayesian, parametric, or local EM models. Each of these approaches has different characteristics and underlying motivations. This paper presents a comprehensive literature review contextualizing both classic and recent approaches to solve this problem. We give a detailed evaluation of the sources of spectral variability and their effect in HI spectra. Furthermore, we propose a new taxonomy that organizes existing work according to a practitioner's point of view, based on the necessary amount of supervision and on the computational cost they require. We also review methods used to construct spectral libraries (which are required by many SU techniques) based on the observed HI, as well as algorithms for library augmentation and reduction. Finally, we conclude the paper with some discussions and an outline of possible future directions for the field.

show abstract