|Copyright||ICIP 2017. All rights reserved.|
|Author(s)||Fablet Ronan1, Viet P.1, Lguensat R.1, Chapron Bertrand2|
|Affiliation(s)||1 : IMT Atlantique, Brest, France.
2 : IFREMER, Brest, France.
|Meeting||ICIP 2017 - IEEE International Conference on Image Processing. 17-20 September 2017, Beijing, China|
|Source||Image Processing (ICIP), 2017 IEEE International Conference on. ISSN 2381-8549 . 5p.|
|Note||Technical program. WQ-PB: Interpolation, Super-resolution, and Mosaicing II. WQ-PB.2|
|Keyword(s)||Data assimilation, irregular sampling, image time series, data-driven methods, Kalman methods|
We address in this paper the reconstruction of irregurlarlysampled image time series with an emphasis on geophysical remote sensing data. We develop a data-driven approach, referred to as an analog assimilation and stated as an ensemble Kalman method. Contrary to model-driven assimilation models, we do not exploit a physically-derived dynamic prior but we build a data-driven dynamic prior from a representative dataset of the considered image dynamics. Our contribution is here to extend analog assimilation to images, which involve high-dimensional state space.We combine patch-based representations to a multiscale PCA-constrained decomposition. Numerical experiments for the interpolation of missing data in satellite-derived ocean remote sensing images demonstrate the relevance of the proposed scheme. It outperforms the classical optimal interpolation with a relative RMSE gain of about 50% for the considered case study.
Fablet Ronan, Viet P., Lguensat R., Chapron Bertrand (2017). Data-driven assimilation of irregularly-sampled image time series. Image Processing (ICIP), 2017 IEEE International Conference on. ISSN 2381-8549 . 5p. http://archimer.ifremer.fr/doc/00403/51440/