Estimating the Number of Endmembers to Use in Spectral Unmixing of Hyperspectral Data with Collaborative Sparsity
From LRDE
- Authors
- Lucas Drumetz, Guillaume Tochon, Jocelyn Chanussot, Christian Jutten
- Where
- Proceedings of the 13th International Conference on Latent Variable Analysis and Signal Separation (LVA-ICA)
- Place
- Grenoble, France
- Type
- inproceedings
- Keywords
- Image
- Date
- 2016-11-22
Abstract
Spectral Umixing (SU) in hyperspectral remote sensing aims at recovering the signatures of the pure materials in the scene (endmembers) and their abundances in each pixel of the image. The usual SU chain does not take spectral variability (SV) into account, and relies on the estimation of the Intrinsic Dimensionality (ID) of the data, related to the number of endmembers (NOE) to use. However, the ID can be significantly overestimated in difficult scenariosand sometimes does not correspond to the desired scale and application dependent NOE. Spurious endmembers are then frequently extracted and included in the model. We propose an algorithm for SU incorporating SV, using collaborative sparsity to discard the least explicative endmembers in the whole image. We compute an algorithmic regularization path for this problem to select the optimal set of endmembers using a statistical criterion. Results on simulated and real data show the interest of the approach.
Documents
Bibtex (lrde.bib)
@InProceedings{ drumetz.17.lva-ica, author = {Lucas Drumetz and Guillaume Tochon and Jocelyn Chanussot and Christian Jutten}, title = {Estimating the Number of Endmembers to Use in Spectral Unmixing of Hyperspectral Data with Collaborative Sparsity}, booktitle = {Proceedings of the 13th International Conference on Latent Variable Analysis and Signal Separation (LVA-ICA)}, year = 2017, address = {Grenoble, France}, month = feb, abstract = {Spectral Umixing (SU) in hyperspectral remote sensing aims at recovering the signatures of the pure materials in the scene (endmembers) and their abundances in each pixel of the image. The usual SU chain does not take spectral variability (SV) into account, and relies on the estimation of the Intrinsic Dimensionality (ID) of the data, related to the number of endmembers (NOE) to use. However, the ID can be significantly overestimated in difficult scenarios, and sometimes does not correspond to the desired scale and application dependent NOE. Spurious endmembers are then frequently extracted and included in the model. We propose an algorithm for SU incorporating SV, using collaborative sparsity to discard the least explicative endmembers in the whole image. We compute an algorithmic regularization path for this problem to select the optimal set of endmembers using a statistical criterion. Results on simulated and real data show the interest of the approach.} }