Diffusion-based inpainting for coding remote-sensing data
Amrani, Naoufal (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions)
Serra Sagristà, Joan (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions)
Peter, Pascal (Saarland University (Alemanya). Mathematical Image Analysis Group)
Weickert, Joachim (Saarland University (Alemanya). Mathematical Image Analysis Group)

Date:	2017
Abstract:	Inpainting techniques based on partial differential equations (PDEs) such as diffusion processes are gaining growing importance as a novel family of image compression methods. Nevertheless, the application of inpainting in the field of hyperspectral imagery has been mainly focused on filling in missing information or dead pixels due to sensor failures. In this paper we propose a novel PDE-based inpainting algorithm to compress hyperspectral images. The method inpaints separately the known data in the spatial and in the spectral dimensions. Then it applies a prediction model to the final inpainting solution to obtain a representation much closer to the original image. Experimental results over a set of hyperspectral images indicate that the proposed algorithm can perform better than a recent proposed extension to prediction-based standard CCSDS-123. 0 at low bitrate, better than JPEG 2000 Part 2 with the DWT 9/7 as a spectral transform at all bit-rates, and competitive to JPEG 2000 with principal component analysis (PCA), the optimal spectral decorrelation transform for Gaussian sources.
Grants:	Ministerio de Economía y Competitividad TIN2015-71126-R Agència de Gestió d'Ajuts Universitaris i de Recerca 2014/SGR-691
Rights:	Tots els drets reservats.
Language:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Published in:	IEEE geoscience and remote sensing letters, Vol. PP, issue 99 (June 2017) , ISSN 1545-598X

DOI: 10.1109/LGRS.2017.2702106

Postprint 5 p, 227.6 KB

The record appears in these collections:
Research literature > UAB research groups literature > Research Centres and Groups (research output) > Engineering > Group on Interactive Coding of Images (GICI)
Articles > Research articles
Articles > Published articles