Robust Linear Spectral Unmixing using Anomaly Detection

TL;DR

This paper introduces a Bayesian method for linear spectral unmixing of hyperspectral images that effectively detects anomalies by modeling outliers and noise, improving accuracy in identifying endmembers and anomalies.

Contribution

The paper proposes a novel Bayesian joint unmixing and anomaly detection algorithm that accounts for anomalies using a Markov random field model, enhancing hyperspectral analysis.

Findings

Accurate unmixing of synthetic and real hyperspectral data.

Effective detection of anomalies in spatial and spectral domains.

Improved identification of outliers compared to existing methods.

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.