Filtering-based Endmember Estimation from Snapshot Spectral Images
Published in 2nd Workshop on Low-Rank Models and Applications (LRMA 2022), 2022
We propose a new endmember estimation method for snapshot spectral imaging (SSI) systems using Fabry-Perot filters. Indeed, such systems only provide a part of the spectral content of a classical multispectral camera and restoring the full datacube from an SSI matrix is named “demosaicing”. However, we recently found that a joint unmixing and demosaicing method allowed a much better unmixing performance than a two-stage approach consisting of a demosaicing step followed by an unmixing one. In this paper, we propose a new approach to estimate endmembers from the SSI image without requiring a demosaicing step. It inverts the Fabry-Perot filters and extends the “pure pixel” framework to the SSI sensor patch level. Our proposed scheme is found to significantly outperform SotA methods.
Recommended citation: Abbas, Kinan, Puigt, Matthieu, Delmaire, Gilles, and Roussel, Gilles. (2022). "Filtering-based endmember estimation from snapshot spectral images." In 2nd Workshop on Low-Rank Models and Applications (LRMA 2022).
Download Paper