Please use this identifier to cite or link to this item:
Title: Super-resolution with selective filter based on adaptive window and variable macro-block size
Authors: Quevedo, Eduardo 
Sánchez, L.
M. Callicó, G. 
Tobajas, F. 
de la Cruz, J.
de Armas, V. 
Sarmiento, R. 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Super-resolution
Variable block size
Image enhancement
Video enhancement
Selective filter
Issue Date: 2018
Journal: Journal of Real-Time Image Processing 
Abstract: Super-resolution (SR) covers a set of techniques whose objective is to improve the spatial resolution of a video sequence or a single frame. In this scope, fusion SR techniques obtain high-resolution (HR) frames taking as a reference several low-resolution (LR) frames contained in a video sequence. This paper is based on a selective filter to decide the best LR frames to be used in the super-resolution process. Additionally, each frame division into macro-blocks (MBs) is analyzed both in a fixed block size approach, which decides which MBs should be used in the process, and in a variable block size approach with an adaptive MB size, which has been developed to set an appropriate frame division into MBs with variable size. These contributions not only improve the quality of video sequences, but also reduce the computational cost of a baseline SR algorithm, avoiding the incorporation of non-correlated data. Furthermore, this paper explains the way in which the enhanced algorithm proposed in it outperforms the quality of typical SR applications, such as underwater imagery, surveillance video, or remote sensing. The results are provided in a test environment to objectively compare the image quality enhancement obtained by bilinear interpolation, by the baseline SR algorithm, and by the proposed methods, thus presenting a quantitative comparison based on peak signal-to-noise ratio (PSNR) and Structural SIMilarity (SSIM) index parameters. The comparison has also been extended to other relevant proposals of the state of the art. The proposed algorithm significantly speeds up the previous ones, allowing real-time execution under certain conditions.
ISSN: 1861-8200
DOI: 10.1007/s11554-015-0489-3
Source: Journal of Real-Time Image Processing [ISSN 1861-8200], v. 15 (2), p. 389-406
Appears in Collections:Artículos
Show full item record


checked on Nov 26, 2023


checked on Jul 9, 2023

Page view(s)

checked on Oct 14, 2023

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.