Online deconvolution for pushbroom hyperspectral imaging systems
Résumé
This paper introduces a framework based on the LMS algorithm for sequential deconvolution of hyperspectral images acquired by pushbroom imaging systems. Considering a sequential model of image blurring phenomenon, we derive a sliding-block regularized LMS algorithm with spatial and spectral regularizers. The performance of the algorithm is evaluated using real hyperspectral data. The role of the hyperparameters is also discussed.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...