Online deconvolution for industrial hyperspectral imaging systems

Yingying Song (1) , El-Hadi Djermoune (1) , Jie Chen (2) , Cédric Richard (3) , David Brie (1)

1 CRAN - Centre de Recherche en Automatique de Nancy
2 Guilin University of Electronic Technology
3 LAGRANGE - Joseph Louis LAGRANGE

This paper proposes a hyperspectral image deconvolution algorithm for the online restoration of hyperspectral images as provided by wiskbroom and pushbroom scanning systems. We introduce a least-mean-squares (LMS)-based framework accounting for the convolution kernel non-causality and including non-quadratic (zero attracting and piece-wise constant) regularization terms. This results in the so-called sliding block regularized LMS (SBR-LMS) which maintains a linear complexity compatible with real-time processing in industrial applications. A model for the algorithm mean and mean-squares transient behavior is derived and the stability condition is studied. Experiments are conducted to assess the role of each hyper-parameter. A key feature of the proposed SBR-LMS is that it outperforms standard approaches in low SNR scenarios such as ultra-fast scanning.

Mots clés: hyperspectral image; online deconvolution; ZA-LMS; LMS

Domaines: Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]

Yingying Song, El-Hadi Djermoune, Jie Chen, Cédric Richard, David Brie. Online deconvolution for industrial hyperspectral imaging systems. SIAM Journal on Imaging Sciences, 2019, 12 (1), pp.54-86. ⟨10.1137/18M1177640⟩. ⟨hal-01801272v3⟩