Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Mutli-Frame Super-Resolution by Enhanced Shift & Add
Al Ismaeil, Kassem; Aouada, Djamila; Mirbach, Bruno et al.
2013In 8th International Symposium on Image and Signal Processing and Analysis
Peer reviewed
 

Files


Full Text
ISPA_09-04-2013.pdf
Author preprint (1.59 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Super-resolution; Pyramidal optical flow; Upsampling
Abstract :
[en] A critical step in multi-frame super-resolution is the registration of frames based on their motion. We improve the performance of current state-of-the-art super-resolution techniques by proposing a more robust and accurate registration as early as in the initialization stage of the high resolution estimate. Indeed, we solve the limitations on scale and motion inherent to the classical Shift & Add approach by upsampling the low resolution frames up to the super-resolution factor prior to estimating motion or to median filtering. This is followed by an appropriate selective optimization, leading to an enhanced Shift & Add. Quantitative and qualitative evaluations have been conducted at two levels; the initial estimation and the final optimized super-resolution. Results show that the proposed algorithm outperforms existing state-of-art methods.
Disciplines :
Computer science
Author, co-author :
Al Ismaeil, Kassem ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Mirbach, Bruno;  iee S.A > Advanced Engineering Department
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
Mutli-Frame Super-Resolution by Enhanced Shift & Add
Publication date :
2013
Event name :
8th International Symposium on Image and Signal Processing and Analysis
Event place :
Trieste, Italy
Event date :
from 04-09-2013 to 06-09-2013
Audience :
International
Main work title :
8th International Symposium on Image and Signal Processing and Analysis
Peer reviewed :
Peer reviewed
Name of the research project :
R-AGR-0686-1 > C11/IS/1204105 : FAVE > 01/01/2012 - 31/12/2014 > OTTERSTEN Björn
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 09 September 2013

Statistics


Number of views
170 (15 by Unilu)
Number of downloads
252 (5 by Unilu)

WoS citations
 
2

Bibliography


Similar publications



Contact ORBilu