Estimating the Number of Endmembers to Use in Spectral Unmixing of Hyperspectral Data with Collaborative Sparsity

Lucas Drumetz 1 Guillaume Tochon 1 Jocelyn Chanussot 1 Christian Jutten 2
1 GIPSA-SIGMAPHY - SIGMAPHY
GIPSA-DIS - Département Images et Signal
2 GIPSA-VIBS - VIBS
GIPSA-DIS - Département Images et Signal
Abstract : Spectral Umixing (SU) in hyperspectral remote sensing aims at recovering the signatures of the pure materials in the scene (endmem-bers) 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.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01479420
Contributor : Christian Jutten <>
Submitted on : Tuesday, February 28, 2017 - 6:27:12 PM
Last modification on : Friday, September 13, 2019 - 12:08:02 PM
Long-term archiving on : Monday, May 29, 2017 - 4:17:40 PM

File

drumetz_lva_ica2017.pdf
Files produced by the author(s)

Identifiers

Citation

Lucas Drumetz, Guillaume Tochon, Jocelyn Chanussot, Christian Jutten. Estimating the Number of Endmembers to Use in Spectral Unmixing of Hyperspectral Data with Collaborative Sparsity. 13th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2017), Olivier Michel; Nadège Thirion-Moreau, Feb 2017, Grenoble, France. pp.381 - 391, ⟨10.1007/978-3-319-53547-0_36⟩. ⟨hal-01479420⟩

Share

Metrics

Record views

647

Files downloads

732