Multifeature Hyperspectral Unmixing Based on Tensor Decomposition - Pôle AI & Ocean Access content directly
Preprints, Working Papers, ... Year : 2022

Multifeature Hyperspectral Unmixing Based on Tensor Decomposition

Démélange hyperspectral multi-caractéristique basé sur la décomposition tensorielle


Hyperspectral unmixing allows to represent mixed pixels as a set of pure materials weighted by their abundances. Spectral features alone are often insufficient, so it is common to rely on other features of the scene. Matrix models become insufficient when the hyperspectral image is represented as a high-order tensor with additional features in a multimodal, multi-feature framework. Tensor models such as canonical polyadic decomposition allow for this kind of unmixing, but lack a general framework and interpretability of the results. In this paper, we propose a methodological framework for multi-feature unmixing based on alternating optimization alternating direction method of multipliers and incorporating abundance sum-to-one constraint (AO-ADMM-ASC), with in-depth mathematical, physical and graphical interpretation and connections with the extended linear mixing model. As additional features, we propose to incorporate mathematical morphology and reframe a previous work on neighborhood patches within our framework. Experiments on real hyperspectral image data show the efficiency of AO-ADMM-ASC and allows an in-depth interpretation of the model. Python and MATLAB implementations of AO-ADMM-ASC are made available at:
Fichier principal
Vignette du fichier
Tensor_HSI_Unmixing_v2.pdf (5.71 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03480890 , version 1 (14-12-2021)
hal-03480890 , version 2 (30-12-2021)
hal-03480890 , version 3 (27-09-2022)
hal-03480890 , version 4 (30-09-2022)
hal-03480890 , version 5 (07-05-2023)
hal-03480890 , version 6 (20-07-2023)
hal-03480890 , version 7 (18-09-2023)


  • HAL Id : hal-03480890 , version 3


Mohamad Jouni, Mauro Dalla Mura, Lucas Drumetz, Pierre Comon. Multifeature Hyperspectral Unmixing Based on Tensor Decomposition. 2022. ⟨hal-03480890v3⟩
443 View
110 Download


Gmail Facebook X LinkedIn More