FAST FUSION OF HYPERSPECTRAL AND MULTISPECTRAL IMAGES : A TUCKER APPROXIMATION APPROACH

Clémence Prévost (1) , Pierre Chainais (1) , Remy Boyer (1)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189

Hyperspectral super-resolution based on coupled Tucker decomposition has been recently considered in the remote sensing community. The state-of-the-art approaches did not fully exploit the coupling information contained in hyperspectral and multispectral images of the same scene. In this paper, we propose a new algorithm that overcomes this limitation. It accounts for both the high-resolution and the low-resolution information in the model, by solving a set of leastsquares problems. In addition, we provide exact recovery conditions for the super-resolution image in the noiseless case. Our simulations show that the proposed algorithm achieves good reconstruction with low complexity.

Mots clés: hyperspectral super-resolution; data fusion; low-rank tensor factorizations; recovery; least-squares problem

Domaines: Traitement du signal et de l'image [eess.SP]

Clémence Prévost, Pierre Chainais, Remy Boyer. FAST FUSION OF HYPERSPECTRAL AND MULTISPECTRAL IMAGES : A TUCKER APPROXIMATION APPROACH. 2022. ⟨hal-03617759⟩