Robust Linear Spectral Unmixing using Anomaly Detection

Research output: Contribution to journalArticle

Abstract

This paper presents a Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data. The model proposed assumes that the pixel reflectances are linear mixtures of unknown endmembers, corrupted by an additional nonlinear term modelling anomalies and additive Gaussian noise. A Markov random field is used for anomaly detection based on the spatial and spectral structures of the anomalies. This allows outliers to be identified in particular regions and wavelengths of the data cube. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding a joint linear unmixing and anomaly detection algorithm. Simulations conducted with synthetic and real hyperspectral images demonstrate the accuracy of the proposed unmixing and outlier detection strategy for the analysis of hyperspectral images.
Original languageEnglish
JournalIEEE Transactions on Computational Imaging
Early online date10 Jul 2015
DOIs
Publication statusPublished - 2015

Fingerprint

anomaly
outlier
reflectance
pixel
detection
wavelength
modeling
simulation

Keywords

  • stat.ME

Cite this

@article{14872382598f48bf965859ed512d6a19,
title = "Robust Linear Spectral Unmixing using Anomaly Detection",
abstract = "This paper presents a Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data. The model proposed assumes that the pixel reflectances are linear mixtures of unknown endmembers, corrupted by an additional nonlinear term modelling anomalies and additive Gaussian noise. A Markov random field is used for anomaly detection based on the spatial and spectral structures of the anomalies. This allows outliers to be identified in particular regions and wavelengths of the data cube. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding a joint linear unmixing and anomaly detection algorithm. Simulations conducted with synthetic and real hyperspectral images demonstrate the accuracy of the proposed unmixing and outlier detection strategy for the analysis of hyperspectral images.",
keywords = "stat.ME",
author = "Yoann Altmann and Steve McLaughlin and Alfred Hero",
year = "2015",
doi = "10.1109/TCI.2015.2455411",
language = "English",
journal = "IEEE Transactions on Computational Imaging",
issn = "2333-9403",
publisher = "IEEE",

}

TY - JOUR

T1 - Robust Linear Spectral Unmixing using Anomaly Detection

AU - Altmann, Yoann

AU - McLaughlin, Steve

AU - Hero, Alfred

PY - 2015

Y1 - 2015

N2 - This paper presents a Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data. The model proposed assumes that the pixel reflectances are linear mixtures of unknown endmembers, corrupted by an additional nonlinear term modelling anomalies and additive Gaussian noise. A Markov random field is used for anomaly detection based on the spatial and spectral structures of the anomalies. This allows outliers to be identified in particular regions and wavelengths of the data cube. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding a joint linear unmixing and anomaly detection algorithm. Simulations conducted with synthetic and real hyperspectral images demonstrate the accuracy of the proposed unmixing and outlier detection strategy for the analysis of hyperspectral images.

AB - This paper presents a Bayesian algorithm for linear spectral unmixing of hyperspectral images that accounts for anomalies present in the data. The model proposed assumes that the pixel reflectances are linear mixtures of unknown endmembers, corrupted by an additional nonlinear term modelling anomalies and additive Gaussian noise. A Markov random field is used for anomaly detection based on the spatial and spectral structures of the anomalies. This allows outliers to be identified in particular regions and wavelengths of the data cube. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding a joint linear unmixing and anomaly detection algorithm. Simulations conducted with synthetic and real hyperspectral images demonstrate the accuracy of the proposed unmixing and outlier detection strategy for the analysis of hyperspectral images.

KW - stat.ME

U2 - 10.1109/TCI.2015.2455411

DO - 10.1109/TCI.2015.2455411

M3 - Article

JO - IEEE Transactions on Computational Imaging

JF - IEEE Transactions on Computational Imaging

SN - 2333-9403

ER -