A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks
Elgohary, M., E. Abd EL-Samie, F., El-Shafai, W., Mohamed, M., H. Abdelhay, E. (2022). A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks. EKB Journal Management System, 47(4), 1-10. doi: 10.21608/bfemu.2022.258300
M. A. Elgohary; Fathi E. Abd EL-Samie; Walid El-Shafai; M. A. Mohamed; E. H. Abdelhay. "A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks". EKB Journal Management System, 47, 4, 2022, 1-10. doi: 10.21608/bfemu.2022.258300
Elgohary, M., E. Abd EL-Samie, F., El-Shafai, W., Mohamed, M., H. Abdelhay, E. (2022). 'A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks', EKB Journal Management System, 47(4), pp. 1-10. doi: 10.21608/bfemu.2022.258300
Elgohary, M., E. Abd EL-Samie, F., El-Shafai, W., Mohamed, M., H. Abdelhay, E. A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks. EKB Journal Management System, 2022; 47(4): 1-10. doi: 10.21608/bfemu.2022.258300

A Proposed Video Super-Resolution Strategy using Wavelet Multi-Scale Convolutional Neural Networks

MEJ- Mansoura Engineering Journal
Article 1, Volume 47, Issue 4, August 2022, Page 1-10  XML PDF (1.6 MB)
Document Type: Research Studies
DOI: 10.21608/bfemu.2022.258300
View on SCiNiTO View on SCiNiTO
Authors
M. A. Elgohary email 1; Fathi E. Abd EL-Samie2; Walid El-Shafai3; M. A. Mohamedorcid 4; E. H. Abdelhay5
1MSc Student, Department of Mechatronics Engineering, High Institute of Engineering and Technology, El-mahalla El-koubra, Egypt
2Professor, Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University Menouf, Egypt
3Assistant Professor, Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University Menouf, Egypt
4Editor in - chief, Dean of the College and Chairman of the Board of Directors, Faculty of Engineering, Mansoura University, professor Communications Engineering Dept., Faculty of Engineering, Mansoura University, Egypt
5Assistant Professor, Department of Electronics and Communications Engineering, Faculty of Engineering, Mansoura University, Mansoura, Egypt
Abstract
High-resolution images are often required and desired for most applications, as they incorporate complementary information. However, the optimal utilization of sensor technology and visual technology to improve picture pixel density is often limited and prohibitively expensive. As a result, employing an image processing method to build a high-resolution image from a low-resolution one is a costly and comprehensive option. The goal of video super-resolution is to restore intricate points and reduce the sensory effects. This research builds on the multi-frame super-resolution approach by using wavelet analysis to train convolutional neural networks (CNNs). For that purpose, the approach begins by applying wavelet decomposition on video segments for multi-scale assessment. Then, several CNNs are trained independently to approximate wavelet multi-scale characterizations. The trained CNNs do inference by regressing wavelet multi-scale characterizations from LR frames, followed by wavelet reconstruction, which produces recovered HR frames. This research presents a learning-based method for preserving fine features in low-resolution multi-frame images captured with various camera zoom lenses. The experimental findings confirm the proposed strategy for restoring difficult frames.
Keywords
Super-Resolution; Convolutional Neural Networks; Wavelet Analysis; Multi-Frame; Multi-Scale Regression; Frequency Domain; Spatial Domain
Statistics
Article View: 292
PDF Download: 174